62 citations · 153 across the 36 of their papers we have counts for
38 papers
Self-Evaluating Recursive Agents
TianYi Lyu, Xiaozhe Li, Yang Li +7
Recursive language-model agents decompose tasks and delegate subtasks to child instances of the same policy, forming a tree of work. Training them, however, is hard: the final outc…
Action from Adjacent Set in Physical Space Outperforms the Best Prediction in World Models
Liangyu Li, Qingwen Liu, Mingqing Liu +1
Controllers based on sampling and latent world models assign a predicted terminal cost to each candidate action sequence, choose the minimum, execute its first action block, and re…
MIRA: Medical Image Reflection for Agentic Diagnosis
Shengzhi Wang, Jun Yang, Kai Wu +11
Medical visual agents can use tools to inspect images and retrieve external knowledge, but indiscriminate tool use may introduce noisy or misleading evidence. Reliable diagnosis th…
Beyond Mode Collapse: Distribution Matching for Diverse Reasoning
Xiaozhe Li, Yang Li, Xinyu Fang +10
On-policy reinforcement learning methods like GRPO suffer from mode collapse: they exhibit reduced solution diversity, concentrating probability mass on a single solution once disc…
Forge: Quality-Aware Reinforcement Learning for NP-Hard Optimization in LLMs
Xiaozhe Li, Xinyu Fang, Shengyuan Ding +5
Large Language Models (LLMs) have achieved remarkable success on reasoning benchmarks through Reinforcement Learning with Verifiable Rewards (RLVR), excelling at tasks such as math…
OPT-BENCH: Evaluating the Iterative Self-Optimization of LLM Agents in Large-Scale Search Spaces
Xiaozhe Li, Jixuan Chen, Xinyu Fang +4
Large Language Models (LLMs) have demonstrated remarkable capabilities in reasoning and tool use. However, the fundamental cognitive faculties essential for problem solving, includ…
World Model Control by Trajectory Reachability Metrics
Liangyu Li, Shengzhi Wang, Libin Qiu +2
Latent world models can learn representations that contain information needed for control, while the downstream controller may still rank candidate actions poorly when it relies on…
Escaping the Context Bottleneck: Active Context Curation for LLM Agents via Reinforcement Learning
Xiaozhe Li, Tianyi Lyu, Yizhao Yang +6
Large Language Models (LLMs) struggle with long-horizon tasks due to the "context bottleneck" and the "lost-in-the-middle" phenomenon, where accumulated noise from verbose environm…
COINBench: Moving Beyond Individual Perspectives to Collective Intent Understanding
Xiaozhe Li, Tianyi Lyu, Siyi Yang +6
Understanding human intent is a high-level cognitive challenge for Large Language Models (LLMs), requiring sophisticated reasoning over noisy, conflicting, and non-linear discourse…
ConsintBench: Evaluating Language Models on Real-World Consumer Intent Understanding
Xiaozhe Li, TianYi Lyu, Siyi Yang +6
Understanding human intent is a complex, high-level task for large language models (LLMs), requiring analytical reasoning, contextual interpretation, dynamic information aggregatio…
NP-Engine: Empowering Optimization Reasoning in Large Language Models with Verifiable Synthetic NP Problems
Xiaozhe Li, Xinyu Fang, Shengyuan Ding +4
Large Language Models (LLMs) have shown strong reasoning capabilities, with models like OpenAI's O-series and DeepSeek R1 excelling at tasks such as mathematics, coding, logic, and…
OPT-BENCH: Evaluating LLM Agent on Large-Scale Search Spaces Optimization Problems
Xiaozhe Li, Jixuan Chen, Xinyu Fang +4
Large Language Models (LLMs) have shown remarkable capabilities in solving diverse tasks. However, their proficiency in iteratively optimizing complex solutions through learning fr…
Beyond Static Scenes: Camera-controllable Background Generation for Human Motion
Mingshuai Yao, Mengting Chen, Qinye Zhou +9
In this paper, we investigate the generation of new video backgrounds given a human foreground video, a camera pose, and a reference scene image. This task presents three key chall…
Squeeze Out Tokens from Sample for Finer-Grained Data Governance
Weixiong Lin, Chen Ju, Haicheng Wang +8
Widely observed data scaling laws, in which error falls off as a power of the training size, demonstrate the diminishing returns of unselective data expansion. Hence, data governan…
Bursting Filter Bubble: Enhancing Serendipity Recommendations with Aligned Large Language Models
Yunjia Xi, Muyan Weng, Wen Chen +9
Recommender systems (RSs) often suffer from the feedback loop phenomenon, e.g., RSs are trained on data biased by their recommendations. This leads to the filter bubble effect that…
SlimGPT: Layer-wise Structured Pruning for Large Language Models
Gui Ling, Ziyang Wang, Yuliang Yan +1
Large language models (LLMs) have garnered significant attention for their remarkable capabilities across various domains, whose vast parameter scales present challenges for practi…
No More Tuning: Prioritized Multi-Task Learning with Lagrangian Differential Multiplier Methods
Zhengxing Cheng, Yuheng Huang, Zhixuan Zhang +2
Given the ubiquity of multi-task in practical systems, Multi-Task Learning (MTL) has found widespread application across diverse domains. In real-world scenarios, these tasks often…
Can video generation replace cinematographers? Research on the cinematic language of generated video
Xiaozhe Li, Kai WU, Siyi Yang +12
Recent advancements in text-to-video (T2V) generation have leveraged diffusion models to enhance visual coherence in videos synthesized from textual descriptions. However, existing…
Advancing Myopia To Holism: Fully Contrastive Language-Image Pre-training
Haicheng Wang, Chen Ju, Weixiong Lin +9
In rapidly evolving field of vision-language models (VLMs), contrastive language-image pre-training (CLIP) has made significant strides, becoming foundation for various downstream…
Counterfactual Learning-Driven Representation Disentanglement for Search-Enhanced Recommendation
Jiajun Cui, Xu Chen, Shuai Xiao +4
For recommender systems in internet platforms, search activities provide additional insights into user interest through query-click interactions with items, and are thus widely use…
NoiseBoost: Alleviating Hallucination with Noise Perturbation for Multimodal Large Language Models
Kai Wu, Boyuan Jiang, Zhengkai Jiang +5
Multimodal large language models (MLLMs) contribute a powerful mechanism to understanding visual information building on large language models. However, MLLMs are notorious for suf…
ReForm-Eval: Evaluating Large Vision Language Models via Unified Re-Formulation of Task-Oriented Benchmarks
Zejun Li, Ye Wang, Mengfei Du +9
Recent years have witnessed remarkable progress in the development of large vision-language models (LVLMs). Benefiting from the strong language backbones and efficient cross-modal…
Graph Contrastive Learning with Multi-Objective for Personalized Product Retrieval in Taobao Search
Longbin Li, Chao Zhang, Sen Li +3
In e-commerce search, personalized retrieval is a crucial technique for improving user shopping experience. Recent works in this domain have achieved significant improvements by th…
Rethinking the Role of Pre-ranking in Large-scale E-Commerce Searching System
Zhixuan Zhang, Yuheng Huang, Dan Ou +4
E-commerce search systems such as Taobao Search, the largest e-commerce searching system in China, aim at providing users with the most preferred items (e.g., products). Due to the…