11 papers
Evaluating Counterfactual Sensitivity to Patient Information in Medication-Safety Reasoning
Zhitian Hou, Yuhang Liu, Pengkai Wang +8
Applying a valid medication-safety rule when its patient-specific conditions are not met can produce an incorrect decision. Existing medical evaluations largely use isolated and fi…
DART: Decoded Attention over Recurrent States for Efficient Long-Context Sequence Modeling
Yixiao Qian, Song Chen, Pengkai Wang +3
Modern language models are built primarily from Transformers, recurrent models, and their hybrid architectures. Transformers rely on token-level attention memories, while recurrent…
Beyond Captions: Context-Grounded Reconstruction for Biomedical Multimodal Continued Pretraining
Guanghao Zhu, Zeyu Liu, Zhitian Hou +10
Biomedical figures are explained not by captions alone but by body-text passages that discuss them. Yet current multimodal corpora typically reduce figures to isolated image-captio…
Not All Disagreement Is Learnable: Token Teachability in On-Policy Distillation
Yuanyi Wang, Su Lu, Yanggan Gu +6
On-policy distillation (OPD) trains a student on its own rollouts with token-level teacher supervision. Recent selective OPD methods exploit the non-uniformity of OPD signals by pr…
E-PMQ: Expert-Guided Post-Merge Quantization with Merged-Weight Anchoring
Wenjun Wang, Yanggan Gu, Shuo Cai +4
Low-resource deployment constraints have made model quantization essential for deploying neural networks while preserving performance. Meanwhile, model merging has become an increa…
Discovering Physical Directions in Weight Space: Composing Neural PDE Experts
Pengkai Wang, Pengwei Liu, Yuanyi Wang +7
Recent advances in neural operators have made partial differential equation (PDE) surrogate modeling increasingly scalable and transferable through large-scale pretraining and in-c…
FeatCal: Feature Calibration for Post-Merging Models
Yanggan Gu, Shuo Cai, Zihao Wang +7
Model merging combines task experts into one model and avoids joint training, retraining, or deploying many expert models, but the merged model often still underperforms task exper…
Geometry Conflict: Explaining and Controlling Forgetting in LLM Continual Post-Training
Yuanyi Wang, Yifan Yang, Su Lu +9
Continual post-training aims to extend large language models (LLMs) with new knowledge, skills, and behaviors, yet it remains unclear when sequential updates enable capability tran…
An Efficient Graph-Transformer Operator for Learning Physical Dynamics with Manifolds Embedding
Pengwei Liu, Xingyu Ren, Pengkai Wang +6
Accurate and efficient physical simulations are essential in science and engineering, yet traditional numerical solvers face significant challenges in computational cost when handl…
InfiMed-ORBIT: Aligning LLMs on Open-Ended Complex Tasks via Rubric-Based Incremental Training
Pengkai Wang, Pengwei Liu, Qi Zuo +3
Reinforcement learning (RL) has powered many recent breakthroughs in large language models (LLMs), especially for tasks where rewards can be computed automatically, such as code ge…
PiRD: Physics-informed Residual Diffusion for Flow Field Reconstruction
Siming Shan, Pengkai Wang, Song Chen +3
The use of machine learning in fluid dynamics is becoming more common to expedite the computation when solving forward and inverse problems of partial differential equations. Yet,…