1 citations · 2 across the 16 of their papers we have counts for
17 papers
Latent Multimodal Memory Reasoning
Cai Ke, Xinghao Chen, Yuanchen Bei +7
Long-term personalized agents are required to reason over distributed history across modalities and evolving dialogue states. While existing flat cross-modal methods compress visua…
What Should a Skill Remember? Quality--Cost Trade-offs in Cost-Aware Skill Rewriting for Language Model Agents
Qinghua Xing, Yinda Chen, Yaping Jin +6
Large language model agents increasingly rely on skills: reusable procedural documents encoding workflows, tool use, implementation patterns, validation checks, and domain rules. S…
What Makes Effective Supervision in Latent Chain-of-Thought: An Information-Theoretic Analysis
Xinghao Chen, Chak Tou Leong, Wenjin Guo +3
Latent Chain-of-Thought (CoT) internalizes reasoning within continuous hidden states, offering a promising alternative to verbose discrete reasoning traces. However, robust latent…
SafeClawBench: Separating Semantic, Audit-Evidence, and Sandbox Harm in Tool-Using LLM Agents
Yuchuan Tian, Mengyu Zheng, Haocheng Mei +5
Tool-using language-model agents introduce security failures that go beyond unsafe text: they can disclose protected objects, write persistent memory, send messages, modify databas…
When Compression Helps and When It Hurts: Condition-Aware Analysis of Chain-of-Thought Distillation
Siyang Lyu, Xinghao Chen, Zhijing Sun +3
Chain-of-Thought (CoT) distillation transfers multi-step reasoning from large reasoning models to smaller students, but verbose teacher traces inflate both training and inference c…
VEFX-Bench: A Holistic Benchmark for Generic Video Editing and Visual Effects
Xiangbo Gao, Sicong Jiang, Bangya Liu +12
As AI-assisted video creation becomes increasingly practical, instruction-guided video editing has become essential for refining generated or captured footage to meet professional…
UniToolCall: Unifying Tool-Use Representation, Data, and Evaluation for LLM Agents
Yijuan Liang, Xinghao Chen, Yifan Ge +5
Tool-use capability is a fundamental component of LLM agents, enabling them to interact with external systems through structured function calls. However, existing research exhibits…
OfficeQA Pro: An Enterprise Benchmark for End-to-End Grounded Reasoning
Krista Opsahl-Ong, Arnav Singhvi, Jasmine Collins +10
We introduce OfficeQA Pro, a benchmark for evaluating AI agents on grounded, multi-document reasoning over a large and heterogeneous document corpus. The corpus consists of U.S. Tr…
AutoDataset: A Lightweight System for Continuous Dataset Discovery and Search
Junzhe Yang, Xinghao Chen, Yunuo Liu +3
The continuous expansion of task-specific datasets has become a major driver of progress in machine learning. However, discovering newly released datasets remains difficult, as exi…
Reasoning Beyond Language: A Comprehensive Survey on Latent Chain-of-Thought Reasoning
Xinghao Chen, Anhao Zhao, Heming Xia +7
Large Language Models (LLMs) have shown impressive performance on complex tasks through Chain-of-Thought (CoT) reasoning. However, conventional CoT relies on explicitly verbalized…
Multimodal Language Models See Better When They Look Shallower
Haoran Chen, Junyan Lin, Xinghao Chen +6
Multimodal large language models (MLLMs) typically extract visual features from the final layers of a pretrained Vision Transformer (ViT). This widespread deep-layer bias, however,…
Integrating Chain-of-Thought for Multimodal Alignment: A Study on 3D Vision-Language Learning
Yanjun Chen, Yirong Sun, Xinghao Chen +4
Chain-of-Thought (CoT) reasoning has proven effective in natural language tasks but remains underexplored in multimodal alignment. This study investigates its integration into 3D v…
MultiConIR: Towards multi-condition Information Retrieval
Xuan Lu, Sifan Liu, Bochao Yin +6
Multi-condition information retrieval (IR) presents a significant, yet underexplored challenge for existing systems. This paper introduces MultiConIR, a benchmark specifically desi…
Unveiling the Key Factors for Distilling Chain-of-Thought Reasoning
Xinghao Chen, Zhijing Sun, Wenjin Guo +8
Large Language Models (LLMs) excel in reasoning tasks through Chain-of-Thought (CoT) prompting. However, CoT prompting greatly increases computational demands, which has prompted g…
Breaking the Pre-Planning Barrier: Adaptive Real-Time Coordination of Heterogeneous UAVs
Yuhan Hu, Yirong Sun, Yanjun Chen +3
Unmanned Aerial Vehicles (UAVs) offer significant potential in dynamic, perception-intensive tasks such as search and rescue and environmental monitoring; however, their effectiven…
The Accuracy Paradox in RLHF: When Better Reward Models Don't Yield Better Language Models
Yanjun Chen, Dawei Zhu, Yirong Sun +3
Reinforcement Learning from Human Feedback significantly enhances Natural Language Processing by aligning language models with human expectations. A critical factor in this alignme…
Fine-Grained and Multi-Dimensional Metrics for Document-Level Machine Translation
Yirong Sun, Dawei Zhu, Yanjun Chen +3
Large language models (LLMs) have excelled in various NLP tasks, including machine translation (MT), yet most studies focus on sentence-level translation. This work investigates th…