9 papers
Memorize Theorems, Not Instances: Probing SFT Generalization through Mathematical Reasoning
Ruiying Peng, Mengyu Yang, Jing Lei +3
Supervised Fine-Tuning (SFT) is widely used for task-specific adaptation, yet recent work shows it systematically undermines reasoning generalization. We argue the root cause is no…
Deeper Thought, Weaker Aim: Understanding and Mitigating Perceptual Impairment during Reasoning in Multimodal Large Language Models
Ruiying Peng, Xueyu Wu, Jing Lei +3
Multimodal large language models (MLLMs) often suffer from perceptual impairments under extended reasoning modes, particularly in visual question answering (VQA) tasks. We identify…
-mem: Efficient Online Memory for Large Language Models
Jingdi Lei, Di Zhang, Junxian Li +7
Large language models increasingly need to accumulate and reuse historical information in long-term assistants and agent systems. Simply expanding the context window is costly and…
Exact Flow Linear Attention: Exact Solution from Continuous-Time Dynamics
Jingdi Lei, Di Zhang, Soujanya Poria
In this paper, we introduce Exact Flow Linear Attention~(EFLA), an exact-flow formulation of delta-rule linear attention. We show that the delta-rule update can be interpreted as a…
MolReFlect: Towards In-Context Fine-grained Alignments between Molecules and Texts
Jiatong Li, Yunqing Liu, Wei Liu +6
Molecule discovery is a pivotal research field, impacting everything from medicine to materials. Recently, Large Language Models (LLMs) have been widely adopted in molecular unders…
OffTopicEval: When Large Language Models Enter the Wrong Chat, Almost Always!
Jingdi Lei, Varun Gumma, Rishabh Bhardwaj +4
Large Language Model (LLM) safety is one of the most pressing challenges for enabling wide-scale deployment. While most studies and global discussions focus on generic harms, such…