23 citations · 33 across the 29 of their papers we have counts for
31 papers
Diagnosing with Insights: Structured Analysis of Agent Failures via Behavioral Abstractions
Jiayi Bi, Yanjie Gao, Yuanmin Xie +4
With the proliferation of LLM agents, the ability to understand and diagnose failures in agents is essential to achieving superior effectiveness and trustworthiness. As agent failu…
Why Does Feedback-Augmented Self-Distillation Fail to Improve Retrieval-Interleaved Search Agents?
Fan Yang, Rui Meng, Yuxin Wen
On-policy self-distillation (OPSD) offers a promising approach for training large language models without relying on a separate teacher model. However, its effectiveness on complex…
TraceVision: Trajectory-Aware Vision-Language Model for Human-Like Spatial Understanding
Fan Yang, Shurong Zheng, Hongyin Zhao +5
Recent Large Vision-Language Models (LVLMs) demonstrate remarkable capabilities in image understanding and natural language generation. However, current approaches focus predominan…
CREM: Compression-Driven Representation Enhancement for Multimodal Retrieval and Comprehension
Lihao Liu, Yan Wang, Biao Yang +10
Multimodal Large Language Models (MLLMs) have shown remarkable success in comprehension tasks such as visual description and visual question answering. However, their direct applic…
ConvApparel: A Benchmark Dataset and Validation Framework for User Simulators in Conversational Recommenders
Ofer Meshi, Krisztian Balog, Sally Goldman +5
The promise of LLM-based user simulators to improve conversational AI is hindered by a critical "realism gap," leading to systems that are optimized for simulated interactions, but…
UniRef-Image-Edit: Towards Scalable and Consistent Multi-Reference Image Editing
Hongyang Wei, Bin Wen, Yancheng Long +22
We present UniRef-Image-Edit, a high-performance multi-modal generation system that unifies single-image editing and multi-image composition within a single framework. Existing dif…
Awakening Dormant Users: Generative Recommendation with Counterfactual Functional Role Reasoning
Huishi Luo, Shuokai Li, Hanchen Yang +10
Awakening dormant users, who remain engaged but exhibit low conversion, is a pivotal driver for incremental GMV growth in large-scale e-commerce platforms. However, existing approa…
Multi-Head Attention as a Source of Catastrophic Forgetting in MoE Transformers
Anrui Chen, Ruijun Huang, Xin Zhang +15
Mixture-of-Experts (MoE) architectures are often considered a natural fit for continual learning because sparse routing should localize updates and reduce interference, yet MoE Tra…
SD-MoE: Spectral Decomposition for Effective Expert Specialization
Ruijun Huang, Fang Dong, Xin Zhang +16
Mixture-of-Experts (MoE) architectures scale Large Language Models via expert specialization induced by conditional computation. In practice, however, expert specialization often f…
Neuro-Symbolic Verification on Instruction Following of LLMs
Yiming Su, Kunzhao Xu, Yanjie Gao +4
A fundamental problem of applying Large Language Models (LLMs) to important applications is that LLMs do not always follow instructions, and violations are often hard to observe or…
Owen-Shapley Policy Optimization: A Principled RL Algorithm for Generative Search LLMs
Abhijnan Nath, Alireza Bagheri Garakani, Tianchen Zhou +3
Large language models are increasingly trained via reinforcement learning for personalized recommendation tasks, but standard methods like GRPO rely on sparse, sequence-level rewar…
Meta Lattice: Model Space Redesign for Cost-Effective Industry-Scale Ads Recommendations
Liang Luo, Yuxin Chen, Zhengyu Zhang +39
The rapidly evolving landscape of products, surfaces, policies, and regulations poses significant challenges for deploying state-of-the-art recommendation models at industry scale,…
Safe2Harm: Semantic Isomorphism Attacks for Jailbreaking Large Language Models
Fan Yang
Large Language Models (LLMs) have demonstrated exceptional performance across various tasks, but their security vulnerabilities can be exploited by attackers to generate harmful co…
MRD: Multi-resolution Retrieval-Detection Fusion for High-Resolution Image Understanding
Fan Yang, Xingping Dong, Xin Yu +3
Understanding high-resolution (HR) images remains a critical challenge for multimodal large language models (MLLMs). Recent approaches leverage vision-based retrieval-augmented gen…
Catastrophic Forgetting in Kolmogorov-Arnold Networks
Mohammad Marufur Rahman, Guanchu Wang, Kaixiong Zhou +2
Catastrophic forgetting is a longstanding challenge in continual learning, where models lose knowledge from earlier tasks when learning new ones. While various mitigation strategie…
FilmSceneDesigner: Chaining Set Design for Procedural Film Scene Generation
Zhifeng Xie, Keyi Zhang, Yiye Yan +4
Film set design plays a pivotal role in cinematic storytelling and shaping the visual atmosphere. However, the traditional process depends on expert-driven manual modeling, which i…
JT-Safe: Intrinsically Enhancing the Safety and Trustworthiness of LLMs
Junlan Feng, Fanyu Meng, Chong Long +12
The hallucination and credibility concerns of large language models (LLMs) are global challenges that the industry is collectively addressing. Recently, a significant amount of adv…
Agent Data Protocol: Unifying Datasets for Diverse, Effective Fine-tuning of LLM Agents
Yueqi Song, Ketan Ramaneti, Zaid Sheikh +18
Public research results on large-scale supervised finetuning of AI agents remain relatively rare, since the collection of agent training data presents unique challenges. In this wo…
What Matters in RL-Based Methods for Object-Goal Navigation? An Empirical Study and A Unified Framework
Hongze Wang, Boyang Sun, Jiaxu Xing +5
Object-Goal Navigation (ObjectNav) is a key capability for deploying mobile robots in everyday environments such as homes, schools, and workplaces. In this task, an agent must loca…
Logics-Parsing Technical Report
Xiangyang Chen, Shuzhao Li, Xiuwen Zhu +7
Recent advances in Large Vision-Language models (LVLM) have spurred significant progress in document parsing task. Compared to traditional pipeline-based methods, end-to-end paradi…
RCR-Router: Efficient Role-Aware Context Routing for Multi-Agent LLM Systems with Structured Memory
Jun Liu, Zhenglun Kong, Changdi Yang +12
Large language model (LLM) agents are increasingly organized into multi-agent systems for complex reasoning and decision-making tasks. However, scaling such systems can substantial…
The Cost of Thinking: Increased Jailbreak Risk in Large Language Models
Fan Yang
Thinking mode has always been regarded as one of the most valuable modes in LLMs. However, we uncover a surprising and previously overlooked phenomenon: LLMs with thinking mode are…
BlueLM-2.5-3B Technical Report
Baojiao Xiong, Boheng Chen, Chengzhi Wang +58
We present BlueLM-2.5-3B, a compact and unified dense Multimodal Large Language Model (MLLM) designed for efficient edge-device deployment, offering strong general-purpose and reas…
GLM-4.5V and GLM-4.1V-Thinking: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learning
V Team, Wenyi Hong, Wenmeng Yu +90
We present GLM-4.1V-Thinking, GLM-4.5V, and GLM-4.6V, a family of vision-language models (VLMs) designed to advance general-purpose multimodal understanding and reasoning. In this…