Direct Nash Optimization: Teaching Language Models to Self-Improve with General Preferences
Paper • 2404.03715 • Published • 62
reward modeling
classroom
AI & ML interests
None defined yet.
Recent Activity
View all activity
tengyangx
authored 7
papers 9 days ago
Exploratory Preference Optimization: Harnessing Implicit Q*-Approximation for Sample-Efficient RLHF
Paper • 2405.21046 • Published • 4
Interpretable Preferences via Multi-Objective Reward Modeling and Mixture-of-Experts
Paper • 2406.12845 • Published • 1
Trajectory Bellman Residual Minimization: A Simple Value-Based Method for LLM Reasoning
Paper • 2505.15311 • Published
POLCA: Stochastic Generative Optimization with LLM
Paper • 2603.14769 • Published • 22
Breaking the Capability Ceiling of LLM Post-Training by Reintroducing Markov States
Paper • 2603.19987 • Published • 9
Understanding Behavior Cloning with Action Quantization
Paper • 2603.20538 • Published • 2
tengyangx
submitted 2
papers to Daily Papers 9 days ago
yifeihe3
authored 6
papers about 1 month ago
Semi-Supervised Reward Modeling via Iterative Self-Training
Paper • 2409.06903 • Published • 1
Towards Understanding the Fragility of Multilingual LLMs against Fine-Tuning Attacks
Paper • 2410.18210 • Published
MergeBench: A Benchmark for Merging Domain-Specialized LLMs
Paper • 2505.10833 • Published • 2
Scalable Data Synthesis for Computer Use Agents with Step-Level Filtering
Paper • 2512.10962 • Published • 3
Localize-and-Stitch: Efficient Model Merging via Sparse Task Arithmetic
Paper • 2408.13656 • Published
Scaling Laws for Multilingual Language Models
Paper • 2410.12883 • Published
hendrydong
authored 4
papers 11 months ago
Fractured Chain-of-Thought Reasoning
Paper • 2505.12992 • Published • 23
Beyond 'Aha!': Toward Systematic Meta-Abilities Alignment in Large Reasoning Models
Paper • 2505.10554 • Published • 120
Scalable Chain of Thoughts via Elastic Reasoning
Paper • 2505.05315 • Published • 26
Optimizing Chain-of-Thought Reasoners via Gradient Variance Minimization in Rejection Sampling and RL
Paper • 2505.02391 • Published • 25
hendrydong
authored a
paper about 1 year ago