115 citations · 160 across the 29 of their papers we have counts for
36 papers
Label-Free Localization and Test-Time Suppression of CLIP's Typographic Circuits
Bohan Liu, Wenqian Ye, Guangzhi Xiong +3
CLIP-based Vision-Language Models have become cornerstones of modern multimodal systems. The cross-modal contrastive objective equips the CLIP vision encoder to both see objects an…
Capturing In-Context Learning Dynamics with Task Operators
Guangzhi Xiong, Zhenghao He, Bohan Liu +3
In-context learning (ICL) enables language models to perform new tasks from demonstrations without weight updates. However, every ICL inference requires processing the full set of…
MemLife: Curating and Reasoning over Long-Term Egocentric Video Memories
Guangzhi Xiong, Xinyuan Zhang, Xiao Yang +14
Long-term egocentric video enables personalized AI assistants to reason about daily life. However, as video histories grow to hundreds of hours spanning months or years, reprocessi…
Rethinking Reasoning Paths as Phase-Structured Trajectories
Zhenghao He, Guangzhi Xiong, Sanchit Sinha +3
Large language models often improve problem-solving performance by generating multi-step reasoning paths, yet how to analyze the hidden states along these paths remains unclear. Ex…
Reliable Parallel Decoding in Masked Diffusion Language Models
Zhenghao He, Bohan Liu, Guangzhi Xiong +1
Masked diffusion language models (MDLMs) can generate text efficiently by predicting multiple masked tokens in parallel, but predictions from the same forward pass are not necessar…
Towards Robustness against Typographic Attack with Training-free Concept Localization
Bohan Liu, Wenqian Ye, Guangzhi Xiong +3
Models trained via Contrastive Language-Image Pretraining (CLIP) serve as the foundational vision encoders for most modern Large Vision Language Models (LVLMs). Despite their wides…
Attention-guided Fine-tuning of Multimodal Large Language Models Improves Chain-of-Thought Reasoning
Sanchit Sinha, Guangzhi Xiong, Bohan Liu +2
The effectiveness of Chain-of-Thought (CoT) prompting in Multimodal Large Language Models (MLLMs) remains uncertain: across several visual reasoning benchmarks, CoT prompting often…
Rethinking Visual Attribution for Chest X-ray Reasoning in Large Vision Language Models
Guangzhi Xiong, Qiao Jin, Sanchit Sinha +2
Large Vision Language Models (LVLMs) show promise in medical applications, but their inability to faithfully ground responses in visual evidence raises serious concerns about clini…
Large Language Models Lack Temporal Awareness of Medical Knowledge
Zihan Guan, Qiao Jin, Guangzhi Xiong +6
The existing methods for evaluating the medical knowledge of Large Language Models (LLMs) are largely based on atemporal examination-style benchmarks, while in reality, medical kno…
Retrieving Counterfactuals Improves Visual In-Context Learning
Guangzhi Xiong, Sanchit Sinha, Zhenghao He +1
Vision-language models (VLMs) have achieved impressive performance across a wide range of multimodal reasoning tasks, but they often struggle to disentangle fine-grained visual att…
Med-V1: Small Language Models for Zero-shot and Scalable Biomedical Evidence Attribution
Qiao Jin, Yin Fang, Lauren He +12
Assessing whether an article supports an assertion is essential for hallucination detection and claim verification. While large language models (LLMs) have the potential to automat…
Neural Additive Experts: Context-Gated Experts for Controllable Model Additivity
Guangzhi Xiong, Sanchit Sinha, Aidong Zhang
The trade-off between interpretability and accuracy remains a core challenge in machine learning. Standard Generalized Additive Models (GAMs) offer clear feature attributions but a…
CASL: Concept-Aligned Sparse Latents for Interpreting Diffusion Models
Zhenghao He, Guangzhi Xiong, Boyang Wang +2
Internal activations of diffusion models encode rich semantic information, but interpreting such representations remains challenging. While Sparse Autoencoders (SAEs) have shown pr…
Triggering Chain-of-Thought via Latent Feature Interventions in Large Language Models
Zhenghao He, Guangzhi Xiong, Bohan Liu +2
Chain-of-Thought (CoT) prompting often improves the reasoning performance of large language models (LLMs), but the internal signal that triggers this behavior remains poorly unders…
Toward Faithful Retrieval-Augmented Generation with Sparse Autoencoders
Guangzhi Xiong, Zhenghao He, Bohan Liu +2
Retrieval-Augmented Generation (RAG) improves the factuality of large language models (LLMs) by grounding outputs in retrieved evidence, but faithfulness failures, where generation…
Concept-RuleNet: Grounded Multi-Agent Neurosymbolic Reasoning in Vision Language Models
Sanchit Sinha, Guangzhi Xiong, Zhenghao He +1
Modern vision-language models (VLMs) deliver impressive predictive accuracy yet offer little insight into 'why' a decision is reached, frequently hallucinating facts, particularly…
COCO-Tree: Compositional Hierarchical Concept Trees for Enhanced Reasoning in Vision Language Models
Sanchit Sinha, Guangzhi Xiong, Aidong Zhang
Compositional reasoning remains a persistent weakness of modern vision language models (VLMs): they often falter when a task hinges on understanding how multiple objects, attribute…
GCAV: A Global Concept Activation Vector Framework for Cross-Layer Consistency in Interpretability
Zhenghao He, Sanchit Sinha, Guangzhi Xiong +1
Concept Activation Vectors (CAVs) provide a powerful approach for interpreting deep neural networks by quantifying their sensitivity to human-defined concepts. However, when comput…
Toward Reliable Scientific Hypothesis Generation: Evaluating Truthfulness and Hallucination in Large Language Models
Guangzhi Xiong, Eric Xie, Corey Williams +5
Large language models (LLMs) have shown significant potential in scientific disciplines such as biomedicine, particularly in hypothesis generation, where they can analyze vast lite…
MedCite: Can Language Models Generate Verifiable Text for Medicine?
Xiao Wang, Mengjue Tan, Qiao Jin +5
Existing LLM-based medical question-answering systems lack citation generation and evaluation capabilities, raising concerns about their adoption in practice. In this work, we intr…
Cell-o1: Training LLMs to Solve Single-Cell Reasoning Puzzles with Reinforcement Learning
Yin Fang, Qiao Jin, Guangzhi Xiong +6
Cell type annotation is a key task in analyzing the heterogeneity of single-cell RNA sequencing data. Although recent foundation models automate this process, they typically annota…
ASCENT-ViT: Attention-based Scale-aware Concept Learning Framework for Enhanced Alignment in Vision Transformers
Sanchit Sinha, Guangzhi Xiong, Aidong Zhang
As Vision Transformers (ViTs) are increasingly adopted in sensitive vision applications, there is a growing demand for improved interpretability. This has led to efforts to forward…
Supervising the search process produces reliable and generalizable information-seeking agents
Guangzhi Xiong, Qiao Jin, Xiao Wang +9
Large language models (LLMs) are transforming web search by shifting from document ranking to synthesizing answers, and are increasingly deployed as autonomous agentic search syste…
Ensuring Safety and Trust: Analyzing the Risks of Large Language Models in Medicine
Yifan Yang, Qiao Jin, Robert Leaman +15
The remarkable capabilities of Large Language Models (LLMs) make them increasingly compelling for adoption in real-world healthcare applications. However, the risks associated with…