Bingning Wang

Towards a Unified View of Large Language Model Post-Training

Amplify Adjacent Token Differences: Enhancing Long Chain-of-Thought Reasoning with Shift-FFN

SSRL: Self-Search Reinforcement Learning

Surrogate Signals from Format and Length: Reinforcement Learning for Solving Mathematical Problems without Ground Truth Answers

VPO: Reasoning Preferences Optimization Based on $\mathcal{V}$-Usable Information

Exploring the Design Space of Visual Context Representation in Video MLLMs

Maximizing Intermediate Checkpoint Value in LLM Pretraining with Bayesian Optimization

KV Shifting Attention Enhances Language Modeling

Needle In A Video Haystack: A Scalable Synthetic Evaluator for Video MLLMs

Extracting and Transferring Abilities For Building Multi-lingual Ability-enhanced Large Language Models

Beyond Filtering: Adaptive Image-Text Quality Enhancement for MLLM Pretraining

ShortGPT: Layers in Large Language Models are More Redundant Than You Expect