2 citations · 4 across the 17 of their papers we have counts for
20 papers
Why Generate a Click? Plug-in Decision Heads for Web Agents
Chengguang Gan, Yunhao Liang, Hanjun Wei +3
Web agents built on vision language models decide every action by generating text such as click(12), although most of that text encodes a choice among a few action types and a few…
Mitigating Video Hallucinations via Attention-Guided Representation Perturbation
Zhixin Cai, Ruoqi Yuan, Xinchen Yang +4
Video large language models (Video LLMs) often generate responses unsupported by the input video. Contrastive decoding (CD) can mitigate these hallucinations, but its effectiveness…
CircuitLens: Reasoning Circuits as Data Selection Signals for Reinforcement Learning with Verifiable Rewards
Zhuofan Chen, Ziqian Jiao, Yikai Cui +3
Reinforcement learning with verifiable rewards (RLVR) is sensitive to which problems a model trains on, yet existing selection criteria--difficulty filtering, hand-curation, reward…
How Output Format Confounds Data Quality and Capability in Instruction Tuning
Chengguang Gan, Hanjun Wei, Yunhao Liang +3
Instruction-tuning data are judged by quality metrics, and tuned models are judged by benchmarks, but both judgments pass through an output interface: the surface format in which a…
MAG: A Web-Agent Benchmark and Harness for Multimodal Action and Guide Generation
Chengguang Gan, Hanjun Wei, Yunhao Liang +3
Digital Adoption Platforms (DAPs) are embedded overlays widely used on web systems to guide users through operations inside a page, helping them get started with unfamiliar interfa…
A Learning-Rate-Gated Failure of GRPO in a Small Language and Vision-Language Model Web Agent: A Controlled Null and Its Mechanism
Chengguang Gan, Zhixi Cai, Yunhao Liang +3
Reinforcement learning with verifiable rewards, and Group Relative Policy Optimization (GRPO) in particular, is now run routinely on a supervised checkpoint in the hope of producin…
What We Talk About When We Talk About LLM Planning: Evidence for Two Distinct Planning Abilities
Sukai Huang, Chenyuan Zhang, Fucai Ke +4
When LLMs exhibit uneven performance across planning tasks, these gaps are often attributed to task difficulty. We argue that this explanation is incomplete, as task-level variatio…
Xetrieval: Explaining Dense Retrieval through Feature Elicitation
Zhixin Cai, Jun Bai, Yang Liu +7
Dense retrieval enables effective semantic matching, yet the semantic factors underlying its relevance scores remain opaque. Sparse autoencoders (SAEs) support feature-level explan…
Mini-BEHAVIOR-Gran: Revealing U-Shaped Effects of Instruction Granularity on Language-Guided Embodied Agents
Sukai Huang, Chenyuan Zhang, Fucai Ke +4
Instruction granularity is an important yet poorly controlled variable in language-guided embodied AI. Existing benchmarks typically pair each task with a single static instruction…
VIEW2SPACE: Studying Multi-View Visual Reasoning from Sparse Observations
Fucai Ke, Zhixi Cai, Boying Li +6
Multi-view visual reasoning is essential for intelligent systems that must understand complex environments from sparse and discrete viewpoints, yet existing research has largely fo…
MATA: A Trainable Hierarchical Automaton System for Multi-Agent Visual Reasoning
Zhixi Cai, Fucai Ke, Kevin Leo +4
Recent vision-language models have strong perceptual ability but their implicit reasoning is hard to explain and easily generates hallucinations on complex queries. Compositional m…
Your Dense Retriever is Secretly an Expeditious Reasoner
Yichi Zhang, Jun Bai, Zhixin Cai +4
Dense retrievers enhance retrieval by encoding queries and documents into continuous vectors, but they often struggle with reasoning-intensive queries. Although Large Language Mode…
JRDB-Reasoning: A Difficulty-Graded Benchmark for Visual Reasoning in Robotics
Simindokht Jahangard, Mehrzad Mohammadi, Yi Shen +2
Recent advances in Vision-Language Models (VLMs) and large language models (LLMs) have greatly enhanced visual reasoning, a key capability for embodied AI agents like robots. Howev…
Explain Before You Answer: A Survey on Compositional Visual Reasoning
Fucai Ke, Joy Hsu, Zhixi Cai +10
Compositional visual reasoning has emerged as a key research frontier in multimodal AI, aiming to endow machines with the human-like ability to decompose visual scenes, ground inte…
M-MRE: Extending the Mutual Reinforcement Effect to Multimodal Information Extraction
Chengguang Gan, Zhixi Cai, Yanbin Wei +3
Mutual Reinforcement Effect (MRE) is an emerging subfield at the intersection of information extraction and model interpretability. MRE aims to leverage the mutual understanding be…
DWIM: Towards Tool-aware Visual Reasoning via Discrepancy-aware Workflow Generation & Instruct-Masking Tuning
Fucai Ke, Vijay Kumar B G, Xingjian Leng +6
Visual reasoning (VR), which is crucial in many fields for enabling human-like visual understanding, remains highly challenging. Recently, compositional visual reasoning approaches…
NAVER: A Neuro-Symbolic Compositional Automaton for Visual Grounding with Explicit Logic Reasoning
Zhixi Cai, Fucai Ke, Simindokht Jahangard +4
Visual Grounding (VG) tasks, such as referring expression detection and segmentation tasks are important for linking visual entities to context, especially in complex reasoning tas…
NEUSIS: A Compositional Neuro-Symbolic Framework for Autonomous Perception, Reasoning, and Planning in Complex UAV Search Missions
Zhixi Cai, Cristian Rojas Cardenas, Kevin Leo +14
This paper addresses the problem of autonomous UAV search missions, where a UAV must locate specific Entities of Interest (EOIs) within a time limit, based on brief descriptions in…
Hier-SLAM: Scaling-up Semantics in SLAM with a Hierarchically Categorical Gaussian Splatting
Boying Li, Zhixi Cai, Yuan-Fang Li +2
We propose Hier-SLAM, a semantic 3D Gaussian Splatting SLAM method featuring a novel hierarchical categorical representation, which enables accurate global 3D semantic mapping, sca…
ASGEA: Exploiting Logic Rules from Align-Subgraphs for Entity Alignment
Yangyifei Luo, Zhuo Chen, Lingbing Guo +4
Entity alignment (EA) aims to identify entities across different knowledge graphs that represent the same real-world objects. Recent embedding-based EA methods have achieved state-…