3 citations · 5 across the 10 of their papers we have counts for
12 papers
Why MLLMs Struggle to Count: Overcoming Individuation and Aggregation Bottlenecks with ConvStack
Liwei Che, Yihao Quan, Sen Fang +4
Multimodal Large Language Models (MLLMs) consistently struggle with fine-grained visual counting, yet the underlying causes remain poorly understood. In this work, we present a mec…
Agent MechSuits: Mechanistic Subspace Safety Steering for Multi-Turn CLI Agents
Weidi Luo, Qiming Zhang, Yihao Quan +5
Command-Line Interface (CLI) agents based on large language models (LLMs) demonstrate remarkable autonomous capabilities, but they also introduce significant safety and misuse risk…
MemEye: A Visual-Centric Evaluation Framework for Multimodal Agent Memory
Minghao Guo, Qingyue Jiao, Zeru Shi +14
Long-term agent memory is increasingly multimodal, yet existing evaluations rarely test whether agents preserve the visual evidence needed for later reasoning. In prior work, many…
Where Fake Citations Are Made: Tracing Field-Level Hallucination to Specific Neurons in LLMs
Yuefei Chen, Yihao Quan, Xiaodong Lin +1
LLMs frequently generate fictitious yet convincing citations, often expressing high confidence even when the underlying reference is wrong. We study this failure across 9 models an…
ART: Attention Replacement Technique to Improve Factuality in LLMs
Ziqin Luo, Yihao Quan, Xiaofeng Zhang +2
Hallucination in large language models (LLMs) continues to be a significant issue, particularly in tasks like question answering, where models often generate plausible yet incorrec…
Reinforcing Consistency in Video MLLMs with Structured Rewards
Yihao Quan, Zeru Shi, Jinman Zhao +1
Multimodal large language models (MLLMs) have achieved remarkable progress in video understanding. However, seemingly plausible outputs often suffer from poor visual and temporal g…
Counting Circuits: Mechanistic Interpretability of Visual Reasoning in Large Vision-Language Models
Liwei Che, Zhiyu Xue, Yihao Quan +7
Counting serves as a simple but powerful test of a Large Vision-Language Model's (LVLM's) reasoning; it forces the model to identify each individual object and then add them all up…
Improving Visual Reasoning with Iterative Evidence Refinement
Zeru Shi, Kai Mei, Yihao Quan +2
Vision language models (VLMs) are increasingly capable of reasoning over images, but robust visual reasoning often requires re-grounding intermediate steps in the underlying visual…
Read the Scene, Not the Script: Outcome-Aware Safety for LLMs
Rui Wu, Yihao Quan, Zeru Shi +3
Safety-aligned Large Language Models (LLMs) still show two dominant failure modes: they are easily jailbroken, or they over-refuse harmless inputs that contain sensitive surface si…
Enhancing Multimodal Large Language Models Complex Reason via Similarity Computation
Xiaofeng Zhang, Fanshuo Zeng, Yihao Quan +2
Multimodal large language models have experienced rapid growth, and numerous different models have emerged. The interpretability of LVLMs remains an under-explored area. Especially…
Seeing Clearly by Layer Two: Enhancing Attention Heads to Alleviate Hallucination in LVLMs
Xiaofeng Zhang, Yihao Quan, Chaochen Gu +6
The hallucination problem in multimodal large language models (MLLMs) remains a common issue. Although image tokens occupy a majority of the input sequence of MLLMs, there is limit…
From Redundancy to Relevance: Information Flow in LVLMs Across Reasoning Tasks
Xiaofeng Zhang, Yihao Quan, Chen Shen +7
Large Vision Language Models (LVLMs) achieve great performance on visual-language reasoning tasks, however, the black-box nature of LVLMs hinders in-depth research on the reasoning…