JUN ZHOU

WSM: Decay-Free Learning Rate Schedule via Checkpoint Merging for LLM Pre-training

Towards Greater Leverage: Scaling Laws for Efficient Mixture-of-Experts Language Models

Bridging the Gap Between Preference Alignment and Machine Unlearning

Not All Code Helps: Disentangling the Impact of Code Data on Mathematical Reasoning in Large Language Models

Towards High Data Efficiency in Reinforcement Learning with Verifiable Reward

Interactive Implicit In-context Learning

Enhancing Cross-task Transfer of Large Language Models via Fourier Activation Steering

MiniOpt: Reasoning to Model and Solve General Optimization Problems with Limited Resources

The Debate on RLVR Reasoning Capability Boundary: Shrinkage, Expansion, or Both? A Two-Stage Dynamic View

Adaptive Mixture of Disentangled Experts for Dynamic Graph Out-of-Distribution Generalization

PruneHal: Reducing Hallucinations in Multi-modal Large Language Models through Adaptive KV Cache Pruning

LLaDA 1.5: Variance-Reduced Preference Optimization for Large Language Diffusion Models

CodeChemist: Test-Time Scaling for Low-Resource Code Generation via Functional Knowledge Transfer

Parameter-wise Weighted Model Editing for Efficient and Retentive LLM Unlearning

HieraQuery: Bridging Multimodal Understanding and High-Quality Generation through Multi-Scale Query Learning

Attention Localization Through Separator Tokens: Unlocking Long Numerical Sequence Processing in LLMs

Beyond Parallel Corpora: Unlocking Autonomous Machine Translation via Autocritical Reinforcement Learning

Xihe: Scalable Zero-shot Time Series Learner via Hierarchical Interleaved Block Attention

Reflective Reinforcement Tool Learning

GQA: Generation Quality Assessment of AIGC Videos based on Human Assessment: Dataset, Scoring and Explanation

Unlocking the Power of Function Vectors for Characterizing and Mitigating Catastrophic Forgetting in Continual Instruction Tuning

Large Language Diffusion Models

Controllable Unlearning for Image-to-Image Generative Models via $\epsilon$-Constrained Optimization

Mix Data or Merge Models? Balancing the Helpfulness, Honesty, and Harmlessness of Large Language Model via Model Merging

MASS: Mathematical Data Selection via Skill Graphs for Pretraining Large Language Models

Effective and Efficient Masked Image Generation Models

ARGenSeg: Image Segmentation with Autoregressive Image Generation Model

ShieldHead: Decoding-time Safeguard for Large Language Models

LLMOPT: Learning to Define and Solve General Optimization Problems from Scratch

Rethinking Causal Ranking: A Balanced Perspective on Uplift Model Evaluation

Relation Augmented Preferential Bayesian Optimization via Preference Propagation

Large Language Diffusion Models

Low-cost Enhancer for Text Attributed Graph Learning via Graph Alignment

R3HF: Reward Redistribution for Enhancing Reinforcement Learning from Human Feedback