14 papers
When Non-Adversarial Noise Hurts Learning: Benchmarking Skill Self-Evolution in Agents
Tao Yu, Zhongtian Luo, Yuchen Long +19
Large language model agents increasingly improve by distilling experience into reusable skills, but errors in that experience can persist in learned rules and affect later tasks. E…
Semantic Reasoning Denoising: Correcting Language Model Reasoning with Semantic Operators
Yujiao Yang
Large language models can produce fluent reasoning traces whose local semantic errors propagate to an incorrect conclusion, while unconstrained self-correction may preserve, amplif…
SCOPE-Router: Cost-Aware Open-Set VLM Routing for Execution-Oriented Tasks
Tao Yu, Yifei Qu, Zhiqing Cui +14
Model routing aims to select the most suitable model from a candidate pool for each query, balancing quality and cost. Existing VLM routing research is limited to traditional VQA e…
Delta-JEPA: Learning Action-Sensitive World Models via Latent Difference Decoding
Zhenghao Zhang, Yuanxiang Wang, Zhenyu Guan +11
Learning visual world models for planning requires compact latent dynamics that remain sensitive to actions, yet reconstruction-free joint-embedding objectives can collapse to acti…
When Seeing Is Not Believing -- A Benchmark for Search-Grounded Video Misinformation Detection
Tao Yu, Yujia Yang, Shenghua Chai +18
Video misinformation increasingly operates at the semantic and evidential level: authentic footage may be selectively edited, temporally reordered, spliced across sources, or augme…
Omni IIE Bench: Benchmarking the Practical Capabilities of Image Editing Models
Yujia Yang, Yuanxiang Wang, Zhenyu Guan +11
While Instruction-based Image Editing (IIE) has achieved significant progress, existing benchmarks pursue task breadth via mixed evaluations. This paradigm obscures a critical fail…
ShotFinder: Imagination-Driven Open-Domain Video Shot Retrieval via Web Search
Tao Yu, Haopeng Jin, Hao Wang +19
In recent years, large language models (LLMs) have made rapid progress in information retrieval, yet existing research has mainly focused on text or static multimodal settings. Ope…
PaperX: A Unified Framework for Multimodal Academic Presentation Generation with Scholar DAG
Tao Yu, Minghui Zhang, Zhiqing Cui +17
Transforming scientific papers into multimodal presentation content is essential for research dissemination but remains labor intensive. Existing automated solutions typically trea…
Beyond Closed-Pool Video Retrieval: A Benchmark and Agent Framework for Real-World Video Search and Moment Localization
Tao Yu, Yujia Yang, Haopeng Jin +17
Traditional video retrieval benchmarks focus on matching precise descriptions to closed video pools, failing to reflect real-world searches characterized by fuzzy, multi-dimensiona…
TRUE: A Trustworthy Unified Explanation Framework for Large Language Model Reasoning
Yujiao Yang
Large language models (LLMs) have demonstrated strong capabilities in complex reasoning tasks, yet their decision-making processes remain difficult to interpret. Existing explanati…
VDE Bench: Evaluating The Capability of Image Editing Models to Modify Visual Documents
Hongzhu Yi, Yujia Yang, Yuanxiang Wang +18
Image editing models can modify visual content through natural language, but editing dense documents requires precise local changes amid tightly coupled text, tables, and layout. W…
RPO:Reinforcement Fine-Tuning with Partial Reasoning Optimization
Hongzhu Yi, Xinming Wang, Zhenghao zhang +12
Within the domain of large language models, reinforcement fine-tuning algorithms necessitate the generation of a complete reasoning trajectory beginning from the input query, which…
Multi-chain Graph Refinement and Selection for Reliable Reasoning in Large Language Models
Yujiao Yang, Jing Lian, Linhui Li
The complex reasoning ability of Large Language Models (LLMs) poses a critical bottleneck for their practical applications. Test-time expansion methods such as Tree-of-Thought (ToT…
Union of Experts: Adapting Hierarchical Routing to Equivalently Decomposed Transformer
Yujiao Yang, Jing Lian, Linhui Li
Mixture-of-Experts (MoE) enhances model performance while maintaining computational efficiency, making it well-suited for large-scale applications. Conventional mixture-of-experts…