19 papers
DRIFT: Transferring Reasoning Priors for Efficient MLLM Fine-Tuning
Chao Huang, Zeliang Zhang, Jiang Liu +7
Multimodal large language models (MLLMs) have made rapid progress, yet their reasoning ability often lags behind strong text-only LLMs. Bridging this gap typically requires large-s…
Does a Global Perspective Help Prune Sparse MoEs Elegantly?
Zeliang Zhang, Nikhil Ghosh, Jiani Liu +2
Empirical scaling laws for language models have encouraged the development of ever-larger LLMs, despite their growing computational and memory costs. Sparse Mixture-of-Experts (MoE…
Can VLMs Truly Forget? Benchmarking Training-Free Visual Concept Unlearning
Zhangyun Tan, Zeliang Zhang, Susan Liang +3
VLMs trained on web-scale data retain sensitive and copyrighted visual concepts that deployment may require removing. Training-based unlearning methods share a structural flaw: fin…
Why Instruction-Based Unlearning Fails in Diffusion Models?
Zeliang Zhang, Rui Sun, Jiani Liu +2
Instruction-based unlearning has proven effective for modifying the behavior of large language models at inference time, but whether this paradigm extends to other generative model…
OPENXRD: A Comprehensive Benchmark Framework for LLM/MLLM XRD Question Answering
Ali Vosoughi, Ayoub Shahnazari, Yufeng Xi +4
We introduce OPENXRD, a comprehensive benchmarking framework for evaluating large language models (LLMs) and multimodal LLMs (MLLMs) in crystallography question answering. The fram…
Training Large Reasoning Models Efficiently via Progressive Thought Encoding
Zeliang Zhang, Xiaodong Liu, Hao Cheng +3
Large reasoning models (LRMs) excel on complex problems but face a critical barrier to efficiency: reinforcement learning (RL) training requires long rollouts for outcome-based rew…