2 citations · 2 across the 14 of their papers we have counts for
14 papers
Buried in Textual Debt: Context Pruning with Visual Evidence Preservation for MLLM Agents
Yuchen Huang, Sijia Li, Jun Zhang +1
Multimodal Large Language Models (MLLMs) are increasingly deployed as multi-step agents, where explicit reasoning supports task decomposition and tool coordination but also accumul…
PACE: Adaptive Budget Allocation for Time-Efficient Embodied Planning
Yuchen Huang, Xijiang Ying, Zhenhua Ma +14
Reasoning-enhanced large language models have achieved remarkable improvements in planning tasks, yet their deployment in embodied systems remains impractical due to prohibitive in…
CDR-Bench: Evaluating Faithful Execution of Compositional, Order-Sensitive Data Refinement Recipes
Yuchen Huang, Xiang Li, Zhenqing Ling +5
Data refinement involves executing multi-step recipes over evolving text states, where both composition and execution order of processing operators determine the outcome. While exi…
GEAR: Granularity-Adaptive Advantage Reweighting for LLM Agents via Self-Distillation
Sijia Li, Yuchen Huang, Zifan Liu +7
Reinforcement learning has become a widely used post-training approach for LLM agents, where training commonly relies on outcome-level rewards that provide only coarse supervision.…
2D or 3D: Who Governs Salience in VLA Models? -- Tri-Stage Token Pruning Framework with Modality Salience Awareness
Zihao Zheng, Sicheng Tian, Zhihao Mao +8
Vision-Language-Action (VLA) models have emerged as the mainstream of embodied intelligence. Recent VLA models have expanded their input modalities from 2D-only to 2D+3D paradigms,…
Environment Scaling for Interactive Agentic Experience Collection: A Survey
Yuchen Huang, Sijia Li, Minghao Liu +5
LLM-based agents can autonomously accomplish complex tasks across various domains. However, to further cultivate capabilities such as adaptive behavior and long-term decision-makin…
Experience-Evolving Multi-Turn Tool-Use Agent with Hybrid Episodic-Procedural Memory
Sijia Li, Yuchen Huang, Zifan Liu +6
As intents unfold and environments change, multi-turn agents face continuously shifting decision contexts. Although reusing past experience is intuitively appealing, existing appro…
CantoASR: Prosody-Aware ASR-LALM Collaboration for Low-Resource Cantonese
Dazhong Chen, Yi-Cheng Lin, Yuchen Huang +5
Automatic speech recognition (ASR) is critical for language accessibility, yet low-resource Cantonese remains challenging due to limited annotated data, six lexical tones, tone san…
CultureCLIP: Empowering CLIP with Cultural Awareness through Synthetic Images and Contextualized Captions
Yuchen Huang, Zhiyuan Fan, Zhitao He +3
Pretrained vision-language models (VLMs) such as CLIP excel in general multimodal comprehension but often struggle to capture nuanced, context-dependent visual cues. This makes it…
MMBoundary: Advancing MLLM Knowledge Boundary Awareness through Reasoning Step Confidence Calibration
Zhitao He, Sandeep Polisetty, Zhiyuan Fan +3
In recent years, multimodal large language models (MLLMs) have made significant progress but continue to face inherent challenges in multimodal reasoning, which requires multi-leve…
DivScore: Zero-Shot Detection of LLM-Generated Text in Specialized Domains
Zhihui Chen, Kai He, Yucheng Huang +2
Detecting LLM-generated text in specialized and high-stakes domains like medicine and law is crucial for combating misinformation and ensuring authenticity. However, current zero-s…
Vision-Language Models Are Not Pragmatically Competent in Referring Expression Generation
Ziqiao Ma, Jing Ding, Xuejun Zhang +6
Referring Expression Generation (REG) is a core task for evaluating the pragmatic competence of vision-language systems, requiring not only accurate semantic grounding but also adh…
Test-Time Code-Switching for Cross-lingual Aspect Sentiment Triplet Extraction
Dongming Sheng, Kexin Han, Hao Li +4
Aspect Sentiment Triplet Extraction (ASTE) is a thriving research area with impressive outcomes being achieved on high-resource languages. However, the application of cross-lingual…
MoveLight: Enhancing Traffic Signal Control through Movement-Centric Deep Reinforcement Learning
Junqi Shao, Chenhao Zheng, Yuxuan Chen +2
This paper introduces MoveLight, a novel traffic signal control system that enhances urban traffic management through movement-centric deep reinforcement learning. By leveraging de…