Self-Rewarding Language Models
Paper
• 2401.10020 • Published
• 152
LLMs
-
-
Orion-14B: Open-source Multilingual Large Language Models
Paper • 2401.12246 • Published • 14 -
MambaByte: Token-free Selective State Space Model
Paper • 2401.13660 • Published • 60 -
MM-LLMs: Recent Advances in MultiModal Large Language Models
Paper • 2401.13601 • Published • 48 -
OLMo: Accelerating the Science of Language Models
Paper • 2402.00838 • Published • 85 -
Dolma: an Open Corpus of Three Trillion Tokens for Language Model Pretraining Research
Paper • 2402.00159 • Published • 65 -
In Search of Needles in a 10M Haystack: Recurrent Memory Finds What LLMs Miss
Paper • 2402.10790 • Published • 42 -
DataDreamer: A Tool for Synthetic Data Generation and Reproducible LLM Workflows
Paper • 2402.10379 • Published • 31 -
Neural Network Diffusion
Paper • 2402.13144 • Published • 100 -
How Easy is It to Fool Your Multimodal LLMs? An Empirical Analysis on Deceptive Prompts
Paper • 2402.13220 • Published • 14 -
LongRoPE: Extending LLM Context Window Beyond 2 Million Tokens
Paper • 2402.13753 • Published • 116 -
OpenCodeInterpreter: Integrating Code Generation with Execution and Refinement
Paper • 2402.14658 • Published • 83 -
Linear Transformers are Versatile In-Context Learners
Paper • 2402.14180 • Published • 7 -
Watermarking Makes Language Models Radioactive
Paper • 2402.14904 • Published • 23 -
ChunkAttention: Efficient Self-Attention with Prefix-Aware KV Cache and Two-Phase Partition
Paper • 2402.15220 • Published • 20 -
Genie: Generative Interactive Environments
Paper • 2402.15391 • Published • 72 -
ChatMusician: Understanding and Generating Music Intrinsically with LLM
Paper • 2402.16153 • Published • 58 -
MegaScale: Scaling Large Language Model Training to More Than 10,000 GPUs
Paper • 2402.15627 • Published • 36 -
MobiLlama: Towards Accurate and Lightweight Fully Transparent GPT
Paper • 2402.16840 • Published • 25 -
The Era of 1-bit LLMs: All Large Language Models are in 1.58 Bits
Paper • 2402.17764 • Published • 627 -
Video as the New Language for Real-World Decision Making
Paper • 2402.17139 • Published • 22 -
Beyond Language Models: Byte Models are Digital World Simulators
Paper • 2402.19155 • Published • 53 -
Resonance RoPE: Improving Context Length Generalization of Large Language Models
Paper • 2403.00071 • Published • 24 -
DenseMamba: State Space Models with Dense Hidden Connection for Efficient Large Language Models
Paper • 2403.00818 • Published • 19 -
GaLore: Memory-Efficient LLM Training by Gradient Low-Rank Projection
Paper • 2403.03507 • Published • 189 -
Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context
Paper • 2403.05530 • Published • 65 -
DeepSeek-VL: Towards Real-World Vision-Language Understanding
Paper • 2403.05525 • Published • 49 -
Synth^2: Boosting Visual-Language Models with Synthetic Captions and Image Embeddings
Paper • 2403.07750 • Published • 23 -
MoAI: Mixture of All Intelligence for Large Language and Vision Models
Paper • 2403.07508 • Published • 77 -
VisionGPT-3D: A Generalized Multimodal Agent for Enhanced 3D Vision Understanding
Paper • 2403.09530 • Published • 10 -
Griffon v2: Advancing Multimodal Perception with High-Resolution Scaling and Visual-Language Co-Referring
Paper • 2403.09333 • Published • 15 -
Agent-FLAN: Designing Data and Methods of Effective Agent Tuning for Large Language Models
Paper • 2403.12881 • Published • 18 -
HyperLLaVA: Dynamic Visual and Language Expert Tuning for Multimodal Large Language Models
Paper • 2403.13447 • Published • 19 -
Mini-Gemini: Mining the Potential of Multi-modality Vision Language Models
Paper • 2403.18814 • Published • 48 -
BioMedLM: A 2.7B Parameter Language Model Trained On Biomedical Text
Paper • 2403.18421 • Published • 23 -
Jamba: A Hybrid Transformer-Mamba Language Model
Paper • 2403.19887 • Published • 112 -
Direct Preference Optimization of Video Large Multimodal Models from Language Model Reward
Paper • 2404.01258 • Published • 12 -
WavLLM: Towards Robust and Adaptive Speech Large Language Model
Paper • 2404.00656 • Published • 11 -
CodeEditorBench: Evaluating Code Editing Capability of Large Language Models
Paper • 2404.03543 • Published • 18 -
LVLM-Intrepret: An Interpretability Tool for Large Vision-Language Models
Paper • 2404.03118 • Published • 25 -
MiniGPT4-Video: Advancing Multimodal LLMs for Video Understanding with Interleaved Visual-Textual Tokens
Paper • 2404.03413 • Published • 27 -
ReFT: Representation Finetuning for Language Models
Paper • 2404.03592 • Published • 101 -
Chinese Tiny LLM: Pretraining a Chinese-Centric Large Language Model
Paper • 2404.04167 • Published • 13 -
LLM2Vec: Large Language Models Are Secretly Powerful Text Encoders
Paper • 2404.05961 • Published • 66 -
Rho-1: Not All Tokens Are What You Need
Paper • 2404.07965 • Published • 94 -
RecurrentGemma: Moving Past Transformers for Efficient Open Language Models
Paper • 2404.07839 • Published • 48 -
Applying Guidance in a Limited Interval Improves Sample and Distribution Quality in Diffusion Models
Paper • 2404.07724 • Published • 14 -
Megalodon: Efficient LLM Pretraining and Inference with Unlimited Context Length
Paper • 2404.08801 • Published • 66 -
TriForce: Lossless Acceleration of Long Sequence Generation with Hierarchical Speculative Decoding
Paper • 2404.11912 • Published • 17 -
AutoCrawler: A Progressive Understanding Web Agent for Web Crawler Generation
Paper • 2404.12753 • Published • 43 -
Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone
Paper • 2404.14219 • Published • 259 -
How Good Are Low-bit Quantized LLaMA3 Models? An Empirical Study
Paper • 2404.14047 • Published • 45 -
FlowMind: Automatic Workflow Generation with LLMs
Paper • 2404.13050 • Published • 34 -
Multi-Head Mixture-of-Experts
Paper • 2404.15045 • Published • 60 -
WildChat: 1M ChatGPT Interaction Logs in the Wild
Paper • 2405.01470 • Published • 64 -
Xmodel-VLM: A Simple Baseline for Multimodal Vision Language Model
Paper • 2405.09215 • Published • 22 -
OpenRLHF: An Easy-to-use, Scalable and High-performance RLHF Framework
Paper • 2405.11143 • Published • 41 -
Imp: Highly Capable Large Multimodal Models for Mobile Devices
Paper • 2405.12107 • Published • 29 -
AlignGPT: Multi-modal Large Language Models with Adaptive Alignment Capability
Paper • 2405.14129 • Published • 14 -
ConvLLaVA: Hierarchical Backbones as Visual Encoder for Large Multimodal Models
Paper • 2405.15738 • Published • 46 -
Stacking Your Transformers: A Closer Look at Model Growth for Efficient LLM Pre-Training
Paper • 2405.15319 • Published • 28 -
NV-Embed: Improved Techniques for Training LLMs as Generalist Embedding Models
Paper • 2405.17428 • Published • 19 -
Value-Incentivized Preference Optimization: A Unified Approach to Online and Offline RLHF
Paper • 2405.19320 • Published • 10 -
Offline Regularised Reinforcement Learning for Large Language Models Alignment
Paper • 2405.19107 • Published • 15 -
Show, Don't Tell: Aligning Language Models with Demonstrated Feedback
Paper • 2406.00888 • Published • 33 -
Xmodel-LM Technical Report
Paper • 2406.02856 • Published • 10 -
Mixture-of-Agents Enhances Large Language Model Capabilities
Paper • 2406.04692 • Published • 59 -
Skywork-MoE: A Deep Dive into Training Techniques for Mixture-of-Experts Language Models
Paper • 2406.06563 • Published • 20 -
Turbo Sparse: Achieving LLM SOTA Performance with Minimal Activated Parameters
Paper • 2406.05955 • Published • 27 -
Magpie: Alignment Data Synthesis from Scratch by Prompting Aligned LLMs with Nothing
Paper • 2406.08464 • Published • 71 -
Discovering Preference Optimization Algorithms with and for Large Language Models
Paper • 2406.08414 • Published • 16 -
HelpSteer2: Open-source dataset for training top-performing reward models
Paper • 2406.08673 • Published • 19 -
Samba: Simple Hybrid State Space Models for Efficient Unlimited Context Language Modeling
Paper • 2406.07522 • Published • 40 -
Self-play with Execution Feedback: Improving Instruction-following Capabilities of Large Language Models
Paper • 2406.13542 • Published • 17 -
Iterative Length-Regularized Direct Preference Optimization: A Case Study on Improving 7B Language Models to GPT-4 Level
Paper • 2406.11817 • Published • 13 -
LongRAG: Enhancing Retrieval-Augmented Generation with Long-context LLMs
Paper • 2406.15319 • Published • 64 -
BigCodeBench: Benchmarking Code Generation with Diverse Function Calls and Complex Instructions
Paper • 2406.15877 • Published • 48 -
Scaling Laws for Linear Complexity Language Models
Paper • 2406.16690 • Published • 23 -
Sparser is Faster and Less is More: Efficient Sparse Attention for Long-Range Transformers
Paper • 2406.16747 • Published • 19 -
OlympicArena Medal Ranks: Who Is the Most Intelligent AI So Far?
Paper • 2406.16772 • Published • 2 -
Unlocking Continual Learning Abilities in Language Models
Paper • 2406.17245 • Published • 30 -
Direct Preference Knowledge Distillation for Large Language Models
Paper • 2406.19774 • Published • 22 -
AutoRAG-HP: Automatic Online Hyper-Parameter Tuning for Retrieval-Augmented Generation
Paper • 2406.19251 • Published • 10 -
RegMix: Data Mixture as Regression for Language Model Pre-training
Paper • 2407.01492 • Published • 40 -
Step-Controlled DPO: Leveraging Stepwise Error for Enhanced Mathematical Reasoning
Paper • 2407.00782 • Published • 24 -
DogeRM: Equipping Reward Models with Domain Knowledge through Model Merging
Paper • 2407.01470 • Published • 7 -
Summary of a Haystack: A Challenge to Long-Context LLMs and RAG Systems
Paper • 2407.01370 • Published • 89 -
MInference 1.0: Accelerating Pre-filling for Long-Context LLMs via Dynamic Sparse Attention
Paper • 2407.02490 • Published • 26 -
To Forget or Not? Towards Practical Knowledge Unlearning for Large Language Models
Paper • 2407.01920 • Published • 17 -
Eliminating Position Bias of Language Models: A Mechanistic Approach
Paper • 2407.01100 • Published • 8 -
DotaMath: Decomposition of Thought with Code Assistance and Self-correction for Mathematical Reasoning
Paper • 2407.04078 • Published • 21 -
LLaMAX: Scaling Linguistic Horizons of LLM by Enhancing Translation Capabilities Beyond 100 Languages
Paper • 2407.05975 • Published • 36 -
InverseCoder: Unleashing the Power of Instruction-Tuned Code LLMs with Inverse-Instruct
Paper • 2407.05700 • Published • 14 -
PAS: Data-Efficient Plug-and-Play Prompt Augmentation System
Paper • 2407.06027 • Published • 10 -
Lookback Lens: Detecting and Mitigating Contextual Hallucinations in Large Language Models Using Only Attention Maps
Paper • 2407.07071 • Published • 12 -
AgentInstruct: Toward Generative Teaching with Agentic Flows
Paper • 2407.03502 • Published • 51 -
Inference Performance Optimization for Large Language Models on CPUs
Paper • 2407.07304 • Published • 53 -
SpreadsheetLLM: Encoding Spreadsheets for Large Language Models
Paper • 2407.09025 • Published • 139 -
Human-like Episodic Memory for Infinite Context LLMs
Paper • 2407.09450 • Published • 62 -
MUSCLE: A Model Update Strategy for Compatible LLM Evolution
Paper • 2407.09435 • Published • 23 -
Transformer Layers as Painters
Paper • 2407.09298 • Published • 15 -
H2O-Danube3 Technical Report
Paper • 2407.09276 • Published • 20 -
Understanding Retrieval Robustness for Retrieval-Augmented Image Captioning
Paper • 2406.02265 • Published • 7 -
Characterizing Prompt Compression Methods for Long Context Inference
Paper • 2407.08892 • Published • 11 -
Qwen2 Technical Report
Paper • 2407.10671 • Published • 168 -
Learning to Refuse: Towards Mitigating Privacy Risks in LLMs
Paper • 2407.10058 • Published • 31 -
Q-Sparse: All Large Language Models can be Fully Sparsely-Activated
Paper • 2407.10969 • Published • 23 -
The Good, The Bad, and The Greedy: Evaluation of LLMs Should Not Ignore Non-Determinism
Paper • 2407.10457 • Published • 24 -
Foundational Autoraters: Taming Large Language Models for Better Automatic Evaluation
Paper • 2407.10817 • Published • 15 -
MMM: Multilingual Mutual Reinforcement Effect Mix Datasets & Test with Open-domain Information Extraction Large Language Models
Paper • 2407.10953 • Published • 5 -
Spectra: A Comprehensive Study of Ternary, Quantized, and FP16 Language Models
Paper • 2407.12327 • Published • 79 -
GoldFinch: High Performance RWKV/Transformer Hybrid with Linear Pre-Fill and Extreme KV-Cache Compression
Paper • 2407.12077 • Published • 57 -
Patch-Level Training for Large Language Models
Paper • 2407.12665 • Published • 17 -
The Art of Saying No: Contextual Noncompliance in Language Models
Paper • 2407.12043 • Published • 5 -
Practical Unlearning for Large Language Models
Paper • 2407.10223 • Published • 4 -
Scaling Laws with Vocabulary: Larger Models Deserve Larger Vocabularies
Paper • 2407.13623 • Published • 56 -
Understanding Reference Policies in Direct Preference Optimization
Paper • 2407.13709 • Published • 17 -
Internal Consistency and Self-Feedback in Large Language Models: A Survey
Paper • 2407.14507 • Published • 46 -
SciCode: A Research Coding Benchmark Curated by Scientists
Paper • 2407.13168 • Published • 17 -
Phi-3 Safety Post-Training: Aligning Language Models with a "Break-Fix" Cycle
Paper • 2407.13833 • Published • 12 -
Knowledge Mechanisms in Large Language Models: A Survey and Perspective
Paper • 2407.15017 • Published • 34 -
Compact Language Models via Pruning and Knowledge Distillation
Paper • 2407.14679 • Published • 39 -
BOND: Aligning LLMs with Best-of-N Distillation
Paper • 2407.14622 • Published • 20 -
DDK: Distilling Domain Knowledge for Efficient Large Language Models
Paper • 2407.16154 • Published • 22 -
Data Mixture Inference: What do BPE Tokenizers Reveal about their Training Data?
Paper • 2407.16607 • Published • 23 -
SeaLLMs 3: Open Foundation and Chat Multilingual Large Language Models for Southeast Asian Languages
Paper • 2407.19672 • Published • 57 -
Self-Training with Direct Preference Optimization Improves Chain-of-Thought Reasoning
Paper • 2407.18248 • Published • 33 -
Mixture of Nested Experts: Adaptive Processing of Visual Tokens
Paper • 2407.19985 • Published • 37 -
Visual Riddles: a Commonsense and World Knowledge Challenge for Large Vision and Language Models
Paper • 2407.19474 • Published • 23 -
ThinK: Thinner Key Cache by Query-Driven Pruning
Paper • 2407.21018 • Published • 32 -
The Llama 3 Herd of Models
Paper • 2407.21783 • Published • 117 -
ShieldGemma: Generative AI Content Moderation Based on Gemma
Paper • 2407.21772 • Published • 14 -
Gemma 2: Improving Open Language Models at a Practical Size
Paper • 2408.00118 • Published • 78 -
Improving Text Embeddings for Smaller Language Models Using Contrastive Fine-tuning
Paper • 2408.00690 • Published • 25 -
Unleashing the Power of Data Tsunami: A Comprehensive Survey on Data Assessment and Selection for Instruction Tuning of Language Models
Paper • 2408.02085 • Published • 19 -
Self-Taught Evaluators
Paper • 2408.02666 • Published • 29 -
Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters
Paper • 2408.03314 • Published • 63 -
Transformer Explainer: Interactive Learning of Text-Generative Models
Paper • 2408.04619 • Published • 175 -
Better Alignment with Instruction Back-and-Forth Translation
Paper • 2408.04614 • Published • 15 -
Learning to Predict Program Execution by Modeling Dynamic Dependency on Code Graphs
Paper • 2408.02816 • Published • 5 -
Gemma Scope: Open Sparse Autoencoders Everywhere All At Once on Gemma 2
Paper • 2408.05147 • Published • 41 -
ToolSandbox: A Stateful, Conversational, Interactive Evaluation Benchmark for LLM Tool Use Capabilities
Paper • 2408.04682 • Published • 18 -
Mutual Reasoning Makes Smaller LLMs Stronger Problem-Solvers
Paper • 2408.06195 • Published • 73 -
LongWriter: Unleashing 10,000+ Word Generation from Long Context LLMs
Paper • 2408.07055 • Published • 68 -
Layerwise Recurrent Router for Mixture-of-Experts
Paper • 2408.06793 • Published • 32 -
Amuro & Char: Analyzing the Relationship between Pre-Training and Fine-Tuning of Large Language Models
Paper • 2408.06663 • Published • 16 -
FuxiTranyu: A Multilingual Large Language Model Trained with Balanced Data
Paper • 2408.06273 • Published • 10 -
Aquila2 Technical Report
Paper • 2408.07410 • Published • 15 -
DeepSeek-Prover-V1.5: Harnessing Proof Assistant Feedback for Reinforcement Learning and Monte-Carlo Tree Search
Paper • 2408.08152 • Published • 61 -
I-SHEEP: Self-Alignment of LLM from Scratch through an Iterative Self-Enhancement Paradigm
Paper • 2408.08072 • Published • 34 -
Training Language Models on the Knowledge Graph: Insights on Hallucinations and Their Detectability
Paper • 2408.07852 • Published • 16 -
FuseChat: Knowledge Fusion of Chat Models
Paper • 2408.07990 • Published • 14 -
BAM! Just Like That: Simple and Efficient Parameter Upcycling for Mixture of Experts
Paper • 2408.08274 • Published • 13 -
Cybench: A Framework for Evaluating Cybersecurity Capabilities and Risk of Language Models
Paper • 2408.08926 • Published • 6 -
TableBench: A Comprehensive and Complex Benchmark for Table Question Answering
Paper • 2408.09174 • Published • 52 -
To Code, or Not To Code? Exploring Impact of Code in Pre-training
Paper • 2408.10914 • Published • 45 -
MagicDec: Breaking the Latency-Throughput Tradeoff for Long Context Generation with Speculative Decoding
Paper • 2408.11049 • Published • 14 -
LLM Pruning and Distillation in Practice: The Minitron Approach
Paper • 2408.11796 • Published • 58 -
FocusLLM: Scaling LLM's Context by Parallel Decoding
Paper • 2408.11745 • Published • 25 -
Hermes 3 Technical Report
Paper • 2408.11857 • Published • 56 -
ConflictBank: A Benchmark for Evaluating the Influence of Knowledge Conflicts in LLM
Paper • 2408.12076 • Published • 12 -
Memory-Efficient LLM Training with Online Subspace Descent
Paper • 2408.12857 • Published • 15 -
SWE-bench-java: A GitHub Issue Resolving Benchmark for Java
Paper • 2408.14354 • Published • 41 -
LlamaDuo: LLMOps Pipeline for Seamless Migration from Service LLMs to Small-Scale Local LLMs
Paper • 2408.13467 • Published • 25 -
MobileQuant: Mobile-friendly Quantization for On-device Language Models
Paper • 2408.13933 • Published • 16 -
Efficient Detection of Toxic Prompts in Large Language Models
Paper • 2408.11727 • Published • 13 -
Writing in the Margins: Better Inference Pattern for Long Context Retrieval
Paper • 2408.14906 • Published • 144 -
The Mamba in the Llama: Distilling and Accelerating Hybrid Models
Paper • 2408.15237 • Published • 42 -
BaichuanSEED: Sharing the Potential of ExtensivE Data Collection and Deduplication by Introducing a Competitive Large Language Model Baseline
Paper • 2408.15079 • Published • 54 -
Leveraging Open Knowledge for Advancing Task Expertise in Large Language Models
Paper • 2408.15915 • Published • 19 -
Efficient LLM Scheduling by Learning to Rank
Paper • 2408.15792 • Published • 20 -
Knowledge Navigator: LLM-guided Browsing Framework for Exploratory Search in Scientific Literature
Paper • 2408.15836 • Published • 14 -
ReMamba: Equip Mamba with Effective Long-Sequence Modeling
Paper • 2408.15496 • Published • 12 -
Auxiliary-Loss-Free Load Balancing Strategy for Mixture-of-Experts
Paper • 2408.15664 • Published • 15 -
SciLitLLM: How to Adapt LLMs for Scientific Literature Understanding
Paper • 2408.15545 • Published • 38 -
CURLoRA: Stable LLM Continual Fine-Tuning and Catastrophic Forgetting Mitigation
Paper • 2408.14572 • Published • 8 -
GIFT-SW: Gaussian noise Injected Fine-Tuning of Salient Weights for LLMs
Paper • 2408.15300 • Published • 3 -
OLMoE: Open Mixture-of-Experts Language Models
Paper • 2409.02060 • Published • 78 -
LongRecipe: Recipe for Efficient Long Context Generalization in Large Languge Models
Paper • 2409.00509 • Published • 42 -
ContextCite: Attributing Model Generation to Context
Paper • 2409.00729 • Published • 14 -
PrivacyLens: Evaluating Privacy Norm Awareness of Language Models in Action
Paper • 2409.00138 • Published • 1 -
LongCite: Enabling LLMs to Generate Fine-grained Citations in Long-context QA
Paper • 2409.02897 • Published • 48 -
Arctic-SnowCoder: Demystifying High-Quality Data in Code Pretraining
Paper • 2409.02326 • Published • 19 -
Attention Heads of Large Language Models: A Survey
Paper • 2409.03752 • Published • 92 -
WildVis: Open Source Visualizer for Million-Scale Chat Logs in the Wild
Paper • 2409.03753 • Published • 19 -
How Do Your Code LLMs Perform? Empowering Code Instruction Tuning with High-Quality Data
Paper • 2409.03810 • Published • 35 -
Configurable Foundation Models: Building LLMs from a Modular Perspective
Paper • 2409.02877 • Published • 32 -
Spinning the Golden Thread: Benchmarking Long-Form Generation in Language Models
Paper • 2409.02076 • Published • 12 -
Towards a Unified View of Preference Learning for Large Language Models: A Survey
Paper • 2409.02795 • Published • 72 -
MemoRAG: Moving towards Next-Gen RAG Via Memory-Inspired Knowledge Discovery
Paper • 2409.05591 • Published • 31 -
Benchmarking Chinese Knowledge Rectification in Large Language Models
Paper • 2409.05806 • Published • 15 -
GroUSE: A Benchmark to Evaluate Evaluators in Grounded Question Answering
Paper • 2409.06595 • Published • 38 -
Gated Slot Attention for Efficient Linear-Time Sequence Modeling
Paper • 2409.07146 • Published • 20 -
Self-Harmonized Chain of Thought
Paper • 2409.04057 • Published • 18 -
Source2Synth: Synthetic Data Generation and Curation Grounded in Real Data Sources
Paper • 2409.08239 • Published • 21 -
Ferret: Federated Full-Parameter Tuning at Scale for Large Language Models
Paper • 2409.06277 • Published • 15 -
On the Diagram of Thought
Paper • 2409.10038 • Published • 13 -
A Comprehensive Evaluation of Quantized Instruction-Tuned Large Language Models: An Experimental Analysis up to 405B
Paper • 2409.11055 • Published • 17 -
Measuring and Enhancing Trustworthiness of LLMs in RAG through Grounded Attributions and Learning to Refuse
Paper • 2409.11242 • Published • 7 -
Qwen2.5-Coder Technical Report
Paper • 2409.12186 • Published • 153 -
LLMs + Persona-Plug = Personalized LLMs
Paper • 2409.11901 • Published • 35 -
Preference Tuning with Human Feedback on Language, Speech, and Vision Tasks: A Survey
Paper • 2409.11564 • Published • 20 -
GRIN: GRadient-INformed MoE
Paper • 2409.12136 • Published • 16 -
Training Language Models to Self-Correct via Reinforcement Learning
Paper • 2409.12917 • Published • 140 -
MMSearch: Benchmarking the Potential of Large Models as Multi-modal Search Engines
Paper • 2409.12959 • Published • 38 -
Scaling Smart: Accelerating Large Language Model Pre-training with Small Model Initialization
Paper • 2409.12903 • Published • 22 -
Language Models Learn to Mislead Humans via RLHF
Paper • 2409.12822 • Published • 11 -
Fact, Fetch, and Reason: A Unified Evaluation of Retrieval-Augmented Generation
Paper • 2409.12941 • Published • 23 -
Hackphyr: A Local Fine-Tuned LLM Agent for Network Security Environments
Paper • 2409.11276 • Published • 10 -
HelloBench: Evaluating Long Text Generation Capabilities of Large Language Models
Paper • 2409.16191 • Published • 41 -
Reward-Robust RLHF in LLMs
Paper • 2409.15360 • Published • 6 -
Programming Every Example: Lifting Pre-training Data Quality like Experts at Scale
Paper • 2409.17115 • Published • 64 -
Boosting Healthcare LLMs Through Retrieved Context
Paper • 2409.15127 • Published • 19 -
NoTeeline: Supporting Real-Time Notetaking from Keypoints with Large Language Models
Paper • 2409.16493 • Published • 10 -
HyperAgent: Generalist Software Engineering Agents to Solve Coding Tasks at Scale
Paper • 2409.16299 • Published • 11 -
MaskLLM: Learnable Semi-Structured Sparsity for Large Language Models
Paper • 2409.17481 • Published • 47 -
The Imperative of Conversation Analysis in the Era of LLMs: A Survey of Tasks, Techniques, and Trends
Paper • 2409.14195 • Published • 12 -
Enhancing Structured-Data Retrieval with GraphRAG: Soccer Data Case Study
Paper • 2409.17580 • Published • 8 -
Modulated Intervention Preference Optimization (MIPO): Keep the Easy, Refine the Difficult
Paper • 2409.17545 • Published • 20 -
Erasing Conceptual Knowledge from Language Models
Paper • 2410.02760 • Published • 14 -
CodeMMLU: A Multi-Task Benchmark for Assessing Code Understanding Capabilities of CodeLLMs
Paper • 2410.01999 • Published • 10 -
Data Selection via Optimal Control for Language Models
Paper • 2410.07064 • Published • 9 -
Falcon Mamba: The First Competitive Attention-free 7B Language Model
Paper • 2410.05355 • Published • 35 -
Holistic Unlearning Benchmark: A Multi-Faceted Evaluation for Text-to-Image Diffusion Model Unlearning
Paper • 2410.05664 • Published • 9 -
MathCoder2: Better Math Reasoning from Continued Pretraining on Model-translated Mathematical Code
Paper • 2410.08196 • Published • 48 -
Benchmarking Agentic Workflow Generation
Paper • 2410.07869 • Published • 29 -
PositionID: LLMs can Control Lengths, Copy and Paste with Explicit Positional Awareness
Paper • 2410.07035 • Published • 17 -
StructRAG: Boosting Knowledge Intensive Reasoning of LLMs via Inference-time Hybrid Information Structurization
Paper • 2410.08815 • Published • 47 -
Multi-Agent Collaborative Data Selection for Efficient LLM Pretraining
Paper • 2410.08102 • Published • 21 -
KV Prediction for Improved Time to First Token
Paper • 2410.08391 • Published • 12 -
Mentor-KD: Making Small Language Models Better Multi-step Reasoners
Paper • 2410.09037 • Published • 4 -
DA-Code: Agent Data Science Code Generation Benchmark for Large Language Models
Paper • 2410.07331 • Published • 5 -
Toward General Instruction-Following Alignment for Retrieval-Augmented Generation
Paper • 2410.09584 • Published • 48 -
Omni-MATH: A Universal Olympiad Level Mathematic Benchmark For Large Language Models
Paper • 2410.07985 • Published • 32 -
LiveXiv -- A Multi-Modal Live Benchmark Based on Arxiv Papers Content
Paper • 2410.10783 • Published • 26 -
Rethinking Data Selection at Scale: Random Selection is Almost All You Need
Paper • 2410.09335 • Published • 16 -
LongMemEval: Benchmarking Chat Assistants on Long-Term Interactive Memory
Paper • 2410.10813 • Published • 14 -
Tree of Problems: Improving structured problem solving with compositionality
Paper • 2410.06634 • Published • 8 -
Thinking LLMs: General Instruction Following with Thought Generation
Paper • 2410.10630 • Published • 20 -
Your Mixture-of-Experts LLM Is Secretly an Embedding Model For Free
Paper • 2410.10814 • Published • 51 -
What Matters in Transformers? Not All Attention is Needed
Paper • 2406.15786 • Published • 31 -
LLMtimesMapReduce: Simplified Long-Sequence Processing using Large Language Models
Paper • 2410.09342 • Published • 39 -
SecCodePLT: A Unified Platform for Evaluating the Security of Code GenAI
Paper • 2410.11096 • Published • 13 -
Agent-as-a-Judge: Evaluate Agents with Agents
Paper • 2410.10934 • Published • 23 -
HumanEval-V: Benchmarking High-Level Visual Reasoning with Complex Diagrams in Coding Tasks
Paper • 2410.12381 • Published • 43 -
JudgeBench: A Benchmark for Evaluating LLM-based Judges
Paper • 2410.12784 • Published • 47 -
PopAlign: Diversifying Contrasting Patterns for a More Comprehensive Alignment
Paper • 2410.13785 • Published • 19 -
A Comparative Study on Reasoning Patterns of OpenAI's o1 Model
Paper • 2410.13639 • Published • 19 -
FlatQuant: Flatness Matters for LLM Quantization
Paper • 2410.09426 • Published • 15 -
Retrospective Learning from Interactions
Paper • 2410.13852 • Published • 10 -
CompassJudger-1: All-in-one Judge Model Helps Model Evaluation and Evolution
Paper • 2410.16256 • Published • 61 -
Baichuan Alignment Technical Report
Paper • 2410.14940 • Published • 51 -
RM-Bench: Benchmarking Reward Models of Language Models with Subtlety and Style
Paper • 2410.16184 • Published • 25 -
Pre-training Distillation for Large Language Models: A Design Space Exploration
Paper • 2410.16215 • Published • 17 -
Aligning Large Language Models via Self-Steering Optimization
Paper • 2410.17131 • Published • 24 -
MiniPLM: Knowledge Distillation for Pre-Training Language Models
Paper • 2410.17215 • Published • 16 -
Scaling Diffusion Language Models via Adaptation from Autoregressive Models
Paper • 2410.17891 • Published • 16 -
LOGO -- Long cOntext aliGnment via efficient preference Optimization
Paper • 2410.18533 • Published • 43 -
Unleashing Reasoning Capability of LLMs via Scalable Question Synthesis from Scratch
Paper • 2410.18693 • Published • 42 -
Why Does the Effective Context Length of LLMs Fall Short?
Paper • 2410.18745 • Published • 17 -
Taipan: Efficient and Expressive State Space Language Models with Selective Attention
Paper • 2410.18572 • Published • 18 -
Skywork-Reward: Bag of Tricks for Reward Modeling in LLMs
Paper • 2410.18451 • Published • 20 -
CCI3.0-HQ: a large-scale Chinese dataset of high quality designed for pre-training large language models
Paper • 2410.18505 • Published • 11 -
Asynchronous RLHF: Faster and More Efficient Off-Policy RL for Language Models
Paper • 2410.18252 • Published • 7 -
Should We Really Edit Language Models? On the Evaluation of Edited Language Models
Paper • 2410.18785 • Published • 7 -
Read-ME: Refactorizing LLMs as Router-Decoupled Mixture of Experts with System Co-Design
Paper • 2410.19123 • Published • 15 -
A Survey of Small Language Models
Paper • 2410.20011 • Published • 46 -
LongReward: Improving Long-context Large Language Models with AI Feedback
Paper • 2410.21252 • Published • 19 -
Fast Best-of-N Decoding via Speculative Rejection
Paper • 2410.20290 • Published • 10 -
Relaxed Recursive Transformers: Effective Parameter Sharing with Layer-wise LoRA
Paper • 2410.20672 • Published • 6 -
CLEAR: Character Unlearning in Textual and Visual Modalities
Paper • 2410.18057 • Published • 209 -
SocialGPT: Prompting LLMs for Social Relation Reasoning via Greedy Segment Optimization
Paper • 2410.21411 • Published • 19 -
Flow-DPO: Improving LLM Mathematical Reasoning through Online Multi-Agent Learning
Paper • 2410.22304 • Published • 18 -
Accelerating Direct Preference Optimization with Prefix Sharing
Paper • 2410.20305 • Published • 6 -
RARe: Retrieval Augmented Retrieval with In-Context Examples
Paper • 2410.20088 • Published • 4 -
CORAL: Benchmarking Multi-turn Conversational Retrieval-Augmentation Generation
Paper • 2410.23090 • Published • 55 -
Stealing User Prompts from Mixture of Experts
Paper • 2410.22884 • Published • 16 -
What Happened in LLMs Layers when Trained for Fast vs. Slow Thinking: A Gradient Perspective
Paper • 2410.23743 • Published • 64 -
SelfCodeAlign: Self-Alignment for Code Generation
Paper • 2410.24198 • Published • 24 -
GlotCC: An Open Broad-Coverage CommonCrawl Corpus and Pipeline for Minority Languages
Paper • 2410.23825 • Published • 4 -
Personalization of Large Language Models: A Survey
Paper • 2411.00027 • Published • 33 -
Hunyuan-Large: An Open-Source MoE Model with 52 Billion Activated Parameters by Tencent
Paper • 2411.02265 • Published • 25 -
LIBMoE: A Library for comprehensive benchmarking Mixture of Experts in Large Language Models
Paper • 2411.00918 • Published • 9 -
Decoding Dark Matter: Specialized Sparse Autoencoders for Interpreting Rare Concepts in Foundation Models
Paper • 2411.00743 • Published • 7 -
SALSA: Soup-based Alignment Learning for Stronger Adaptation in RLHF
Paper • 2411.01798 • Published • 8 -
LoRA-Contextualizing Adaptation of Large Multimodal Models for Long Document Understanding
Paper • 2411.01106 • Published • 4 -
HtmlRAG: HTML is Better Than Plain Text for Modeling Retrieved Knowledge in RAG Systems
Paper • 2411.02959 • Published • 71 -
Mixture-of-Transformers: A Sparse and Scalable Architecture for Multi-Modal Foundation Models
Paper • 2411.04996 • Published • 50 -
M3DocRAG: Multi-modal Retrieval is What You Need for Multi-page Multi-document Understanding
Paper • 2411.04952 • Published • 29 -
Parameter-Efficient Fine-Tuning of Large Language Models for Unit Test Generation: An Empirical Study
Paper • 2411.02462 • Published • 10 -
OpenCoder: The Open Cookbook for Top-Tier Code Large Language Models
Paper • 2411.04905 • Published • 127 -
Chinese SimpleQA: A Chinese Factuality Evaluation for Large Language Models
Paper • 2411.07140 • Published • 35 -
IOPO: Empowering LLMs with Complex Instruction Following via Input-Output Preference Optimization
Paper • 2411.06208 • Published • 21 -
Stronger Models are NOT Stronger Teachers for Instruction Tuning
Paper • 2411.07133 • Published • 38 -
Large Language Models Can Self-Improve in Long-context Reasoning
Paper • 2411.08147 • Published • 65 -
Direct Preference Optimization Using Sparse Feature-Level Constraints
Paper • 2411.07618 • Published • 17 -
Top-nσ: Not All Logits Are You Need
Paper • 2411.07641 • Published • 24 -
SlimLM: An Efficient Small Language Model for On-Device Document Assistance
Paper • 2411.09944 • Published • 12 -
Adaptive Decoding via Latent Preference Optimization
Paper • 2411.09661 • Published • 10 -
Building Trust: Foundations of Security, Safety and Transparency in AI
Paper • 2411.12275 • Published • 11 -
SymDPO: Boosting In-Context Learning of Large Multimodal Models with Symbol Demonstration Direct Preference Optimization
Paper • 2411.11909 • Published • 22 -
Loss-to-Loss Prediction: Scaling Laws for All Datasets
Paper • 2411.12925 • Published • 5 -
Marco-o1: Towards Open Reasoning Models for Open-Ended Solutions
Paper • 2411.14405 • Published • 61 -
Hymba: A Hybrid-head Architecture for Small Language Models
Paper • 2411.13676 • Published • 47 -
Do I Know This Entity? Knowledge Awareness and Hallucinations in Language Models
Paper • 2411.14257 • Published • 14 -
UnifiedCrawl: Aggregated Common Crawl for Affordable Adaptation of LLMs on Low-Resource Languages
Paper • 2411.14343 • Published • 7 -
Patience Is The Key to Large Language Model Reasoning
Paper • 2411.13082 • Published • 7 -
TÜLU 3: Pushing Frontiers in Open Language Model Post-Training
Paper • 2411.15124 • Published • 67 -
A Flexible Large Language Models Guardrail Development Methodology Applied to Off-Topic Prompt Detection
Paper • 2411.12946 • Published • 22 -
O1 Replication Journey -- Part 2: Surpassing O1-preview through Simple Distillation, Big Progress or Bitter Lesson?
Paper • 2411.16489 • Published • 45 -
From Generation to Judgment: Opportunities and Challenges of LLM-as-a-judge
Paper • 2411.16594 • Published • 39 -
MH-MoE:Multi-Head Mixture-of-Experts
Paper • 2411.16205 • Published • 26 -
VisualLens: Personalization through Visual History
Paper • 2411.16034 • Published • 18 -
LLMs Do Not Think Step-by-step In Implicit Reasoning
Paper • 2411.15862 • Published • 9 -
All Languages Matter: Evaluating LMMs on Culturally Diverse 100 Languages
Paper • 2411.16508 • Published • 10 -
Training and Evaluating Language Models with Template-based Data Generation
Paper • 2411.18104 • Published • 3 -
Beyond Examples: High-level Automated Reasoning Paradigm in In-Context Learning via MCTS
Paper • 2411.18478 • Published • 37 -
LLM Teacher-Student Framework for Text Classification With No Manually Annotated Data: A Case Study in IPTC News Topic Classification
Paper • 2411.19638 • Published • 6 -
o1-Coder: an o1 Replication for Coding
Paper • 2412.00154 • Published • 44 -
TinyFusion: Diffusion Transformers Learned Shallow
Paper • 2412.01199 • Published • 14 -
VLsI: Verbalized Layers-to-Interactions from Large to Small Vision Language Models
Paper • 2412.01822 • Published • 16 -
Free Process Rewards without Process Labels
Paper • 2412.01981 • Published • 34 -
Truth or Mirage? Towards End-to-End Factuality Evaluation with LLM-OASIS
Paper • 2411.19655 • Published • 20 -
OCR Hinders RAG: Evaluating the Cascading Impact of OCR on Retrieval-Augmented Generation
Paper • 2412.02592 • Published • 24 -
Surveying the Effects of Quality, Diversity, and Complexity in Synthetic Data From Large Language Models
Paper • 2412.02980 • Published • 15 -
Weighted-Reward Preference Optimization for Implicit Model Fusion
Paper • 2412.03187 • Published • 12 -
Evaluating Language Models as Synthetic Data Generators
Paper • 2412.03679 • Published • 47 -
Monet: Mixture of Monosemantic Experts for Transformers
Paper • 2412.04139 • Published • 13 -
Marco-LLM: Bridging Languages via Massive Multilingual Training for Cross-Lingual Enhancement
Paper • 2412.04003 • Published • 10 -
EXAONE 3.5: Series of Large Language Models for Real-world Use Cases
Paper • 2412.04862 • Published • 50 -
Training Large Language Models to Reason in a Continuous Latent Space
Paper • 2412.06769 • Published • 94 -
Evaluating and Aligning CodeLLMs on Human Preference
Paper • 2412.05210 • Published • 50 -
Granite Guardian
Paper • 2412.07724 • Published • 18 -
KaSA: Knowledge-Aware Singular-Value Adaptation of Large Language Models
Paper • 2412.06071 • Published • 9 -
Phi-4 Technical Report
Paper • 2412.08905 • Published • 122 -
SmolTulu: Higher Learning Rate to Batch Size Ratios Can Lead to Better Reasoning in SLMs
Paper • 2412.08347 • Published • 4 -
GReaTer: Gradients over Reasoning Makes Smaller Language Models Strong Prompt Optimizers
Paper • 2412.09722 • Published • 5 -
Smaller Language Models Are Better Instruction Evolvers
Paper • 2412.11231 • Published • 28 -
SPaR: Self-Play with Tree-Search Refinement to Improve Instruction-Following in Large Language Models
Paper • 2412.11605 • Published • 18 -
The Open Source Advantage in Large Language Models (LLMs)
Paper • 2412.12004 • Published • 10 -
Mix-LN: Unleashing the Power of Deeper Layers by Combining Pre-LN and Post-LN
Paper • 2412.13795 • Published • 20 -
How to Synthesize Text Data without Model Collapse?
Paper • 2412.14689 • Published • 53 -
Offline Reinforcement Learning for LLM Multi-Step Reasoning
Paper • 2412.16145 • Published • 38 -
SCOPE: Optimizing Key-Value Cache Compression in Long-context Generation
Paper • 2412.13649 • Published • 21 -
MixLLM: LLM Quantization with Global Mixed-precision between Output-features and Highly-efficient System Design
Paper • 2412.14590 • Published • 15 -
RobustFT: Robust Supervised Fine-tuning for Large Language Models under Noisy Response
Paper • 2412.14922 • Published • 88 -
Outcome-Refining Process Supervision for Code Generation
Paper • 2412.15118 • Published • 19 -
DRT-o1: Optimized Deep Reasoning Translation via Long Chain-of-Thought
Paper • 2412.17498 • Published • 22 -
NILE: Internal Consistency Alignment in Large Language Models
Paper • 2412.16686 • Published • 8 -
ReMoE: Fully Differentiable Mixture-of-Experts with ReLU Routing
Paper • 2412.14711 • Published • 16 -
Ensembling Large Language Models with Process Reward-Guided Tree Search for Better Complex Reasoning
Paper • 2412.15797 • Published • 18 -
Token-Budget-Aware LLM Reasoning
Paper • 2412.18547 • Published • 46 -
Safeguard Fine-Tuned LLMs Through Pre- and Post-Tuning Model Merging
Paper • 2412.19512 • Published • 9 -
Efficiently Serving LLM Reasoning Programs with Certaindex
Paper • 2412.20993 • Published • 36 -
BoostStep: Boosting mathematical capability of Large Language Models via improved single-step reasoning
Paper • 2501.03226 • Published • 43 -
Test-time Computing: from System-1 Thinking to System-2 Thinking
Paper • 2501.02497 • Published • 45 -
ToolHop: A Query-Driven Benchmark for Evaluating Large Language Models in Multi-Hop Tool Use
Paper • 2501.02506 • Published • 10 -
REINFORCE++: A Simple and Efficient Approach for Aligning Large Language Models
Paper • 2501.03262 • Published • 104 -
rStar-Math: Small LLMs Can Master Math Reasoning with Self-Evolved Deep Thinking
Paper • 2501.04519 • Published • 288 -
URSA: Understanding and Verifying Chain-of-thought Reasoning in Multimodal Mathematics
Paper • 2501.04686 • Published • 53 -
Enabling Scalable Oversight via Self-Evolving Critic
Paper • 2501.05727 • Published • 72 -
Multiagent Finetuning: Self Improvement with Diverse Reasoning Chains
Paper • 2501.05707 • Published • 20 -
The Lessons of Developing Process Reward Models in Mathematical Reasoning
Paper • 2501.07301 • Published • 100 -
Transformer^2: Self-adaptive LLMs
Paper • 2501.06252 • Published • 55 -
O1 Replication Journey -- Part 3: Inference-time Scaling for Medical Reasoning
Paper • 2501.06458 • Published • 31 -
SPAM: Spike-Aware Adam with Momentum Reset for Stable LLM Training
Paper • 2501.06842 • Published • 16 -
MiniMax-01: Scaling Foundation Models with Lightning Attention
Paper • 2501.08313 • Published • 300 -
OmniThink: Expanding Knowledge Boundaries in Machine Writing through Thinking
Paper • 2501.09751 • Published • 46 -
Towards Large Reasoning Models: A Survey of Reinforced Reasoning with Large Language Models
Paper • 2501.09686 • Published • 41 -
Demons in the Detail: On Implementing Load Balancing Loss for Training Specialized Mixture-of-Expert Models
Paper • 2501.11873 • Published • 67 -
Reasoning Language Models: A Blueprint
Paper • 2501.11223 • Published • 33 -
Condor: Enhance LLM Alignment with Knowledge-Driven Data Synthesis and Refinement
Paper • 2501.12273 • Published • 14 -
Test-Time Preference Optimization: On-the-Fly Alignment via Iterative Textual Feedback
Paper • 2501.12895 • Published • 61 -
Autonomy-of-Experts Models
Paper • 2501.13074 • Published • 44 -
O1-Pruner: Length-Harmonizing Fine-Tuning for O1-Like Reasoning Pruning
Paper • 2501.12570 • Published • 28 -
Step-KTO: Optimizing Mathematical Reasoning through Stepwise Binary Feedback
Paper • 2501.10799 • Published • 15 -
Qwen2.5-1M Technical Report
Paper • 2501.15383 • Published • 72 -
Parameters vs FLOPs: Scaling Laws for Optimal Sparsity for Mixture-of-Experts Language Models
Paper • 2501.12370 • Published • 11 -
Return of the Encoder: Maximizing Parameter Efficiency for SLMs
Paper • 2501.16273 • Published • 5 -
Over-Tokenized Transformer: Vocabulary is Generally Worth Scaling
Paper • 2501.16975 • Published • 32 -
Low-Rank Adapters Meet Neural Architecture Search for LLM Compression
Paper • 2501.16372 • Published • 12 -
Virus: Harmful Fine-tuning Attack for Large Language Models Bypassing Guardrail Moderation
Paper • 2501.17433 • Published • 10 -
Reward-Guided Speculative Decoding for Efficient LLM Reasoning
Paper • 2501.19324 • Published • 39 -
Constitutional Classifiers: Defending against Universal Jailbreaks across Thousands of Hours of Red Teaming
Paper • 2501.18837 • Published • 10 -
The Differences Between Direct Alignment Algorithms are a Blur
Paper • 2502.01237 • Published • 113 -
Can LLMs Maintain Fundamental Abilities under KV Cache Compression?
Paper • 2502.01941 • Published • 14 -
SmolLM2: When Smol Goes Big -- Data-Centric Training of a Small Language Model
Paper • 2502.02737 • Published • 255 -
Token Assorted: Mixing Latent and Text Tokens for Improved Language Model Reasoning
Paper • 2502.03275 • Published • 18 -
PILAF: Optimal Human Preference Sampling for Reward Modeling
Paper • 2502.04270 • Published • 12 -
CMoE: Fast Carving of Mixture-of-Experts for Efficient LLM Inference
Paper • 2502.04416 • Published • 12 -
Lossless Acceleration of Large Language Models with Hierarchical Drafting based on Temporal Locality in Speculative Decoding
Paper • 2502.05609 • Published • 18 -
Distillation Scaling Laws
Paper • 2502.08606 • Published • 47 -
DPO-Shift: Shifting the Distribution of Direct Preference Optimization
Paper • 2502.07599 • Published • 15 -
LLM Pretraining with Continuous Concepts
Paper • 2502.08524 • Published • 30 -
Mediator: Memory-efficient LLM Merging with Less Parameter Conflicts and Uncertainty Based Routing
Paper • 2502.04411 • Published • 4 -
InfiniteHiP: Extending Language Model Context Up to 3 Million Tokens on a Single GPU
Paper • 2502.08910 • Published • 148 -
DarwinLM: Evolutionary Structured Pruning of Large Language Models
Paper • 2502.07780 • Published • 18 -
ReLearn: Unlearning via Learning for Large Language Models
Paper • 2502.11190 • Published • 30 -
CRANE: Reasoning with constrained LLM generation
Paper • 2502.09061 • Published • 21 -
SafeRoute: Adaptive Model Selection for Efficient and Accurate Safety Guardrails in Large Language Models
Paper • 2502.12464 • Published • 28 -
Injecting Domain-Specific Knowledge into Large Language Models: A Comprehensive Survey
Paper • 2502.10708 • Published • 4 -
Craw4LLM: Efficient Web Crawling for LLM Pretraining
Paper • 2502.13347 • Published • 30 -
InfiR : Crafting Effective Small Language Models and Multimodal Small Language Models in Reasoning
Paper • 2502.11573 • Published • 9 -
Thus Spake Long-Context Large Language Model
Paper • 2502.17129 • Published • 73 -
Drop-Upcycling: Training Sparse Mixture of Experts with Partial Re-initialization
Paper • 2502.19261 • Published • 6 -
LongRoPE2: Near-Lossless LLM Context Window Scaling
Paper • 2502.20082 • Published • 36 -
Predictive Data Selection: The Data That Predicts Is the Data That Teaches
Paper • 2503.00808 • Published • 56 -
Chain of Draft: Thinking Faster by Writing Less
Paper • 2502.18600 • Published • 50 -
Large-Scale Data Selection for Instruction Tuning
Paper • 2503.01807 • Published • 14 -
Babel: Open Multilingual Large Language Models Serving Over 90% of Global Speakers
Paper • 2503.00865 • Published • 64 -
Fine-Tuning Small Language Models for Domain-Specific AI: An Edge AI Perspective
Paper • 2503.01933 • Published • 13 -
FuseChat-3.0: Preference Optimization Meets Heterogeneous Model Fusion
Paper • 2503.04222 • Published • 15 -
RePO: ReLU-based Preference Optimization
Paper • 2503.07426 • Published • 2 -
Block Diffusion: Interpolating Between Autoregressive and Diffusion Language Models
Paper • 2503.09573 • Published • 75 -
Cost-Optimal Grouped-Query Attention for Long-Context LLMs
Paper • 2503.09579 • Published • 5 -
WikiAutoGen: Towards Multi-Modal Wikipedia-Style Article Generation
Paper • 2503.19065 • Published • 11 -
AdaptiVocab: Enhancing LLM Efficiency in Focused Domains through Lightweight Vocabulary Adaptation
Paper • 2503.19693 • Published • 76 -
AdaMMS: Model Merging for Heterogeneous Multimodal Large Language Models with Unsupervised Coefficient Optimization
Paper • 2503.23733 • Published • 10 -
DiaTool-DPO: Multi-Turn Direct Preference Optimization for Tool-Augmented Large Language Models
Paper • 2504.02882 • Published • 7 -
OLMoTrace: Tracing Language Model Outputs Back to Trillions of Training Tokens
Paper • 2504.07096 • Published • 77 -
C3PO: Critical-Layer, Core-Expert, Collaborative Pathway Optimization for Test-Time Expert Re-Mixing
Paper • 2504.07964 • Published • 62 -
Genius: A Generalizable and Purely Unsupervised Self-Training Framework For Advanced Reasoning
Paper • 2504.08672 • Published • 55 -
DataDecide: How to Predict Best Pretraining Data with Small Experiments
Paper • 2504.11393 • Published • 18 -
A Minimalist Approach to LLM Reasoning: from Rejection Sampling to Reinforce
Paper • 2504.11343 • Published • 19 -
BitNet b1.58 2B4T Technical Report
Paper • 2504.12285 • Published • 83 -
A Strategic Coordination Framework of Small LLMs Matches Large LLMs in Data Synthesis
Paper • 2504.12322 • Published • 28 -
Generative AI Act II: Test Time Scaling Drives Cognition Engineering
Paper • 2504.13828 • Published • 18 -
Efficient Pretraining Length Scaling
Paper • 2504.14992 • Published • 20 -
Can Large Language Models Help Multimodal Language Analysis? MMLA: A Comprehensive Benchmark
Paper • 2504.16427 • Published • 18 -
The Sparse Frontier: Sparse Attention Trade-offs in Transformer LLMs
Paper • 2504.17768 • Published • 14 -
TF1-EN-3M: Three Million Synthetic Moral Fables for Training Small, Open Language Models
Paper • 2504.20605 • Published • 14 -
Beyond One-Size-Fits-All: Inversion Learning for Highly Effective NLG Evaluation Prompts
Paper • 2504.21117 • Published • 26 -
Grokking in the Wild: Data Augmentation for Real-World Multi-Hop Reasoning with Transformers
Paper • 2504.20752 • Published • 94 -
Sentient Agent as a Judge: Evaluating Higher-Order Social Cognition in Large Language Models
Paper • 2505.02847 • Published • 29 -
Qwen3 Technical Report
Paper • 2505.09388 • Published • 334 -
Mergenetic: a Simple Evolutionary Model Merging Library
Paper • 2505.11427 • Published • 14 -
Multi-Token Prediction Needs Registers
Paper • 2505.10518 • Published • 14 -
Chain-of-Model Learning for Language Model
Paper • 2505.11820 • Published • 121 -
Model Merging in Pre-training of Large Language Models
Paper • 2505.12082 • Published • 40 -
QwenLong-L1: Towards Long-Context Large Reasoning Models with Reinforcement Learning
Paper • 2505.17667 • Published • 88 -
MIRIAD: Augmenting LLMs with millions of medical query-response pairs
Paper • 2506.06091 • Published • 11 -
MiniCPM4: Ultra-Efficient LLMs on End Devices
Paper • 2506.07900 • Published • 95 -
Resa: Transparent Reasoning Models via SAEs
Paper • 2506.09967 • Published • 21 -
FlexOlmo: Open Language Models for Flexible Data Use
Paper • 2507.07024 • Published • 10 -
KV Cache Steering for Inducing Reasoning in Small Language Models
Paper • 2507.08799 • Published • 40 -
Mixture-of-Recursions: Learning Dynamic Recursive Depths for Adaptive Token-Level Computation
Paper • 2507.10524 • Published • 72 -
LayerCake: Token-Aware Contrastive Decoding within Large Language Model Layers
Paper • 2507.04404 • Published • 22 -
A Survey of Context Engineering for Large Language Models
Paper • 2507.13334 • Published • 261 -
RedOne: Revealing Domain-specific LLM Post-Training in Social Networking Services
Paper • 2507.10605 • Published • 9 -
MUR: Momentum Uncertainty guided Reasoning for Large Language Models
Paper • 2507.14958 • Published • 47 -
SmallThinker: A Family of Efficient Large Language Models Natively Trained for Local Deployment
Paper • 2507.20984 • Published • 58 -
Falcon-H1: A Family of Hybrid-Head Language Models Redefining Efficiency and Performance
Paper • 2507.22448 • Published • 70 -
Sculptor: Empowering LLMs with Cognitive Agency via Active Context Management
Paper • 2508.04664 • Published • 13 -
OpenMed NER: Open-Source, Domain-Adapted State-of-the-Art Transformers for Biomedical NER Across 12 Public Datasets
Paper • 2508.01630 • Published • 14 -
On the Generalization of SFT: A Reinforcement Learning Perspective with Reward Rectification
Paper • 2508.05629 • Published • 183 -
GeRe: Towards Efficient Anti-Forgetting in Continual Learning of LLM via General Samples Replay
Paper • 2508.04676 • Published • 4 -
ST-Raptor: LLM-Powered Semi-Structured Table Question Answering
Paper • 2508.18190 • Published • 7 -
Soft Tokens, Hard Truths
Paper • 2509.19170 • Published • 16 -
Artificial Hippocampus Networks for Efficient Long-Context Modeling
Paper • 2510.07318 • Published • 31 -
A Survey of Vibe Coding with Large Language Models
Paper • 2510.12399 • Published • 50 -
DaMo: Data Mixing Optimizer in Fine-tuning Multimodal LLMs for Mobile Phone Agents
Paper • 2510.19336 • Published • 17 -
Motif 2 12.7B technical report
Paper • 2511.07464 • Published • 39 -
DoPE: Denoising Rotary Position Embedding
Paper • 2511.09146 • Published • 97 -
DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models
Paper • 2512.02556 • Published • 256 -
Beyond Real: Imaginary Extension of Rotary Position Embeddings for Long-Context LLMs
Paper • 2512.07525 • Published • 59 -
Olmo 3
Paper • 2512.13961 • Published • 29 -
DataFlow: An LLM-Driven Framework for Unified Data Preparation and Workflow Automation in the Era of Data-Centric AI
Paper • 2512.16676 • Published • 219 -
Can LLMs Clean Up Your Mess? A Survey of Application-Ready Data Preparation with LLMs
Paper • 2601.17058 • Published • 188