SPaR: Self-Play with Tree-Search Refinement to Improve Instruction-Following in Large Language Models
Paper
• 2412.11605 • Published
• 18
ShowAndTell
-
-
Byte Latent Transformer: Patches Scale Better Than Tokens
Paper • 2412.09871 • Published • 108 -
Fourier Position Embedding: Enhancing Attention's Periodic Extension for Length Generalization
Paper • 2412.17739 • Published • 41 -
SKETCH: Structured Knowledge Enhanced Text Comprehension for Holistic Retrieval
Paper • 2412.15443 • Published • 10 -
ProgCo: Program Helps Self-Correction of Large Language Models
Paper • 2501.01264 • Published • 26 -
SDPO: Segment-Level Direct Preference Optimization for Social Agents
Paper • 2501.01821 • Published • 20 -
ToolHop: A Query-Driven Benchmark for Evaluating Large Language Models in Multi-Hop Tool Use
Paper • 2501.02506 • Published • 10 -
PRMBench: A Fine-grained and Challenging Benchmark for Process-Level Reward Models
Paper • 2501.03124 • Published • 14 -
Evaluating Sample Utility for Data Selection by Mimicking Model Weights
Paper • 2501.06708 • Published • 5 -
Atla Selene Mini: A General Purpose Evaluation Model
Paper • 2501.17195 • Published • 35 -
Exploring the Limit of Outcome Reward for Learning Mathematical Reasoning
Paper • 2502.06781 • Published • 58 -
SpargeAttn: Accurate Sparse Attention Accelerating Any Model Inference
Paper • 2502.18137 • Published • 60 -
StructFlowBench: A Structured Flow Benchmark for Multi-turn Instruction Following
Paper • 2502.14494 • Published • 15 -
Agentic Reward Modeling: Integrating Human Preferences with Verifiable Correctness Signals for Reliable Reward Systems
Paper • 2502.19328 • Published • 23 -
Can Large Language Models Detect Errors in Long Chain-of-Thought Reasoning?
Paper • 2502.19361 • Published • 28 -
Towards an AI co-scientist
Paper • 2502.18864 • Published • 52 -
Predictive Data Selection: The Data That Predicts Is the Data That Teaches
Paper • 2503.00808 • Published • 56 -
From Hours to Minutes: Lossless Acceleration of Ultra Long Sequence Generation up to 100K Tokens
Paper • 2502.18890 • Published • 30 -
SampleMix: A Sample-wise Pre-training Data Mixing Strategey by Coordinating Data Quality and Diversity
Paper • 2503.01506 • Published • 10 -
General Reasoning Requires Learning to Reason from the Get-go
Paper • 2502.19402 • Published • 5 -
LADDER: Self-Improving LLMs Through Recursive Problem Decomposition
Paper • 2503.00735 • Published • 23 -
Process-based Self-Rewarding Language Models
Paper • 2503.03746 • Published • 39 -
IFIR: A Comprehensive Benchmark for Evaluating Instruction-Following in Expert-Domain Information Retrieval
Paper • 2503.04644 • Published • 21 -
Know You First and Be You Better: Modeling Human-Like User Simulators via Implicit Profiles
Paper • 2502.18968 • Published • 3 -
TruthPrInt: Mitigating LVLM Object Hallucination Via Latent Truthful-Guided Pre-Intervention
Paper • 2503.10602 • Published • 4 -
Temporal Consistency for LLM Reasoning Process Error Identification
Paper • 2503.14495 • Published • 11 -
EvalTree: Profiling Language Model Weaknesses via Hierarchical Capability Trees
Paper • 2503.08893 • Published • 6 -
Discovering Knowledge Deficiencies of Language Models on Massive Knowledge Base
Paper • 2503.23361 • Published • 5 -
Bridging Evolutionary Multiobjective Optimization and GPU Acceleration via Tensorization
Paper • 2503.20286 • Published • 3 -
ScholarCopilot: Training Large Language Models for Academic Writing with Accurate Citations
Paper • 2504.00824 • Published • 43 -
Agentic Knowledgeable Self-awareness
Paper • 2504.03553 • Published • 27 -
Heimdall: test-time scaling on the generative verification
Paper • 2504.10337 • Published • 33 -
TextArena
Paper • 2504.11442 • Published • 30 -
Efficient Process Reward Model Training via Active Learning
Paper • 2504.10559 • Published • 13 -
AI-University: An LLM-based platform for instructional alignment to scientific classrooms
Paper • 2504.08846 • Published • 9 -
Learning Adaptive Parallel Reasoning with Language Models
Paper • 2504.15466 • Published • 44 -
Self-Generated In-Context Examples Improve LLM Agents for Sequential Decision-Making Tasks
Paper • 2505.00234 • Published • 26 -
100 Days After DeepSeek-R1: A Survey on Replication Studies and More Directions for Reasoning Language Models
Paper • 2505.00551 • Published • 36 -
Toward Evaluative Thinking: Meta Policy Optimization with Evolving Reward Models
Paper • 2504.20157 • Published • 37 -
TreeHop: Generate and Filter Next Query Embeddings Efficiently for Multi-hop Question Answering
Paper • 2504.20114 • Published • 4 -
SPC: Evolving Self-Play Critic via Adversarial Games for LLM Reasoning
Paper • 2504.19162 • Published • 18 -
Enhancing LLM Reasoning with Iterative DPO: A Comprehensive Empirical Investigation
Paper • 2503.12854 • Published -
LLaMA-Omni2: LLM-based Real-time Spoken Chatbot with Autoregressive Streaming Speech Synthesis
Paper • 2505.02625 • Published • 23 -
Beyond One-Size-Fits-All: Inversion Learning for Highly Effective NLG Evaluation Prompts
Paper • 2504.21117 • Published • 26 -
CORG: Generating Answers from Complex, Interrelated Contexts
Paper • 2505.00023 • Published • 9 -
RetroInfer: A Vector-Storage Approach for Scalable Long-Context LLM Inference
Paper • 2505.02922 • Published • 28 -
Scalable Chain of Thoughts via Elastic Reasoning
Paper • 2505.05315 • Published • 26 -
X-Reasoner: Towards Generalizable Reasoning Across Modalities and Domains
Paper • 2505.03981 • Published • 15 -
AutoLibra: Agent Metric Induction from Open-Ended Feedback
Paper • 2505.02820 • Published • 3 -
Phare: A Safety Probe for Large Language Models
Paper • 2505.11365 • Published • 7 -
ConvSearch-R1: Enhancing Query Reformulation for Conversational Search with Reasoning via Reinforcement Learning
Paper • 2505.15776 • Published • 11 -
BARREL: Boundary-Aware Reasoning for Factual and Reliable LRMs
Paper • 2505.13529 • Published • 11 -
Text Generation Beyond Discrete Token Sampling
Paper • 2505.14827 • Published • 10 -
Scaling Diffusion Transformers Efficiently via μP
Paper • 2505.15270 • Published • 35 -
TabSTAR: A Foundation Tabular Model With Semantically Target-Aware Representations
Paper • 2505.18125 • Published • 112 -
QwenLong-CPRS: Towards infty-LLMs with Dynamic Context Optimization
Paper • 2505.18092 • Published • 43 -
Quartet: Native FP4 Training Can Be Optimal for Large Language Models
Paper • 2505.14669 • Published • 78 -
Learning to Reason without External Rewards
Paper • 2505.19590 • Published • 29 -
Can Large Language Models Infer Causal Relationships from Real-World Text?
Paper • 2505.18931 • Published • 1 -
MiniCPM4: Ultra-Efficient LLMs on End Devices
Paper • 2506.07900 • Published • 95 -
ExpertLongBench: Benchmarking Language Models on Expert-Level Long-Form Generation Tasks with Structured Checklists
Paper • 2506.01241 • Published • 9 -
What Is Seen Cannot Be Unseen: The Disruptive Effect of Knowledge Conflict on Large Language Models
Paper • 2506.06485 • Published • 5 -
Cartridges: Lightweight and general-purpose long context representations via self-study
Paper • 2506.06266 • Published • 7 -
Improving large language models with concept-aware fine-tuning
Paper • 2506.07833 • Published • 3 -
HASHIRU: Hierarchical Agent System for Hybrid Intelligent Resource Utilization
Paper • 2506.04255 • Published • 5 -
Reflect, Retry, Reward: Self-Improving LLMs via Reinforcement Learning
Paper • 2505.24726 • Published • 277 -
MemMamba: Rethinking Memory Patterns in State Space Model
Paper • 2510.03279 • Published • 73