Search, Verify and Feedback: Towards Next Generation Post-training Paradigm of Foundation Models via Verifier Engineering
Paper
•
2411.11504
•
Published
•
23
LLM
-
-
Top-nσ: Not All Logits Are You Need
Paper • 2411.07641 • Published • 23 -
Adaptive Decoding via Latent Preference Optimization
Paper • 2411.09661 • Published • 10 -
When Precision Meets Position: BFloat16 Breaks Down RoPE in Long-Context Training
Paper • 2411.13476 • Published • 16 -
HuggingFaceTB/smoltalk
Viewer • Updated • 2.2M • 5.01k • 369 -
Hymba: A Hybrid-head Architecture for Small Language Models
Paper • 2411.13676 • Published • 45 -
TÜLU 3: Pushing Frontiers in Open Language Model Post-Training
Paper • 2411.15124 • Published • 66 -
Star Attention: Efficient LLM Inference over Long Sequences
Paper • 2411.17116 • Published • 55 -
O1 Replication Journey -- Part 2: Surpassing O1-preview through Simple Distillation, Big Progress or Bitter Lesson?
Paper • 2411.16489 • Published • 47 -
MH-MoE:Multi-Head Mixture-of-Experts
Paper • 2411.16205 • Published • 28 -
nGPT: Normalized Transformer with Representation Learning on the Hypersphere
Paper • 2410.01131 • Published • 10 -
O1-OPEN/OpenO1-SFT
Viewer • Updated • 77.7k • 466 • 382 -
AI-MO/NuminaMath-CoT
Viewer • Updated • 860k • 12.7k • 500 -
GAIR/o1-journey
Viewer • Updated • 327 • 39 • 134 -
allenai/tulu-3-sft-mixture
Viewer • Updated • 939k • 14.6k • 181 -
CASIA-LM/ChineseWebText2.0
Viewer • Updated • 2k • 1.63k • 26 -
Yi-Lightning Technical Report
Paper • 2412.01253 • Published • 28 -
Training Large Language Models to Reason in a Continuous Latent Space
Paper • 2412.06769 • Published • 89 -
Weighted-Reward Preference Optimization for Implicit Model Fusion
Paper • 2412.03187 • Published • 12 -
Phi-4 Technical Report
Paper • 2412.08905 • Published • 121 -
SPaR: Self-Play with Tree-Search Refinement to Improve Instruction-Following in Large Language Models
Paper • 2412.11605 • Published • 18 -
Mix-LN: Unleashing the Power of Deeper Layers by Combining Pre-LN and Post-LN
Paper • 2412.13795 • Published • 20 -
Qwen2.5 Technical Report
Paper • 2412.15115 • Published • 376 -
A Post-Training Enhanced Optimization Approach for Small Language Models
Paper • 2411.02939 • Published -
amphora/QwQ-LongCoT-130K
Viewer • Updated • 133k • 99 • 150 -
How to Synthesize Text Data without Model Collapse?
Paper • 2412.14689 • Published • 52 -
O1-OPEN/OpenO1-SFT-Ultra
Viewer • Updated • 18.7M • 96 • 55 -
RobustFT: Robust Supervised Fine-tuning for Large Language Models under Noisy Response
Paper • 2412.14922 • Published • 88 -
DRT-o1: Optimized Deep Reasoning Translation via Long Chain-of-Thought
Paper • 2412.17498 • Published • 22 -
B-STaR: Monitoring and Balancing Exploration and Exploitation in Self-Taught Reasoners
Paper • 2412.17256 • Published • 47 -
OpenRFT: Adapting Reasoning Foundation Model for Domain-specific Tasks with Reinforcement Fine-Tuning
Paper • 2412.16849 • Published • 9 -
rStar-Math: Small LLMs Can Master Math Reasoning with Self-Evolved Deep Thinking
Paper • 2501.04519 • Published • 285 -
MiniMax-01: Scaling Foundation Models with Lightning Attention
Paper • 2501.08313 • Published • 298 -
OpenCSG Chinese Corpus: A Series of High-quality Chinese Datasets for LLM Training
Paper • 2501.08197 • Published • 9 -
simplescaling/s1K
Viewer • Updated • 1k • 1.22k • 226 -
Infi-MM/InfiMM-WebMath-40B
Viewer • Updated • 22.8M • 2.15k • 68 -
Exploring the Limit of Outcome Reward for Learning Mathematical Reasoning
Paper • 2502.06781 • Published • 59 -
Technologies on Effectiveness and Efficiency: A Survey of State Spaces Models
Paper • 2503.11224 • Published • 28 -
The Lessons of Developing Process Reward Models in Mathematical Reasoning
Paper • 2501.07301 • Published • 99 -
70% Size, 100% Accuracy: Lossless LLM Compression for Efficient GPU Inference via Dynamic-Length Float
Paper • 2504.11651 • Published • 31 -
Paper2Code: Automating Code Generation from Scientific Papers in Machine Learning
Paper • 2504.17192 • Published • 120 -
bnadimi/PyraNet-Verilog
Viewer • Updated • 692k • 477 • 16 -
AdaptThink: Reasoning Models Can Learn When to Think
Paper • 2505.13417 • Published • 82 -
Multi-Token Prediction Needs Registers
Paper • 2505.10518 • Published • 14 -
Quartet: Native FP4 Training Can Be Optimal for Large Language Models
Paper • 2505.14669 • Published • 77 -
Distilling LLM Agent into Small Models with Retrieval and Code Tools
Paper • 2505.17612 • Published • 81 -
J1: Incentivizing Thinking in LLM-as-a-Judge via Reinforcement Learning
Paper • 2505.10320 • Published • 24 -
SeerAttention-R: Sparse Attention Adaptation for Long Reasoning
Paper • 2506.08889 • Published • 23 -
QuantAgent: Price-Driven Multi-Agent LLMs for High-Frequency Trading
Paper • 2509.09995 • Published • 14 -
SimpleVLA-RL: Scaling VLA Training via Reinforcement Learning
Paper • 2509.09674 • Published • 78 -
Causal Attention with Lookahead Keys
Paper • 2509.07301 • Published • 21 -
A Survey of Reinforcement Learning for Large Reasoning Models
Paper • 2509.08827 • Published • 183 -
Why Low-Precision Transformer Training Fails: An Analysis on Flash Attention
Paper • 2510.04212 • Published • 22 -
InternVLA-M1: A Spatially Guided Vision-Language-Action Framework for Generalist Robot Policy
Paper • 2510.13778 • Published • 16 -
Direct Multi-Token Decoding
Paper • 2510.11958 • Published • 5 -
QeRL: Beyond Efficiency -- Quantization-enhanced Reinforcement Learning for LLMs
Paper • 2510.11696 • Published • 165 -
Attention Is All You Need for KV Cache in Diffusion LLMs
Paper • 2510.14973 • Published • 36