2 citations · 2 across the 24 of their papers we have counts for
28 papers
Revealing Structured Heterogeneity
Christopher Turansick
In this paper, we study models of restricted heterogeneity. While the random utility model allows for arbitrary heterogeneity among rational types, we consider the case when an ana…
Learning Native Reflection in Unified Models with Interleaved Reinforcement Learning
Yijia Fan, Ziqi Huang, Zhongang Cai +5
Unified multimodal models can both look at and render images, so in principle they can repair their own generations: diagnose what an image gets wrong, revise it, observe the resul…
Argus: A General-Purpose Agentic Reasoning Runtime for Long-Horizon Tasks
Boxiu Li, Zimo Wen, Yijia Fan +24
Long-horizon reasoning requires an agentic runtime that can persist when evidence supports its current approach and pivot when measurements reveal failure, hidden constraints, or a…
RESOURCE2SKILL: Distilling Executable Agent Skills from Human-Created Multimodal Resources
Yijia Fan, Zonglin Di, Zimo Wen +8
Skills are a useful abstraction for software agents, turning human and agent experience into reusable procedural knowledge. Yet existing skill libraries are mostly hand-written, te…
Decoupling Endpoint and Semantic Transition Learning for Zero-Shot Composed Image Retrieval
Mingyu Liu, Sihan Huang, Yijia Fan +4
Zero-shot composed image retrieval (ZS-CIR) retrieves a target image from a reference image and a text modification without human-annotated CIR triplets. Projection-based ZS-CIR me…
Covering Human Action Space for Computer Use: Data Synthesis and Benchmark
Miaosen Zhang, Xiaohan Zhao, Zhihong Tan +14
Computer-use agents (CUAs) automate on-screen work, as illustrated by GPT-5.4 and Claude. Yet their reliability on complex, low-frequency interactions is still poor, limiting user…
Spectral Gating Networks
Jusheng Zhang, Yijia Fan, Kaitong Cai +5
Gating mechanisms are ubiquitous, yet a complementary question in feed-forward networks remains under-explored: how to introduce frequency-rich expressivity without sacrificing sta…
Why Keep Your Doubts to Yourself? Trading Visual Uncertainties in Multi-Agent Bandit Systems
Jusheng Zhang, Yijia Fan, Kaitong Cai +6
Vision-Language Models (VLMs) enable powerful multi-agent systems, but scaling them is economically unsustainable: coordinating heterogeneous agents under information asymmetry oft…
3D-Agent:Tri-Modal Multi-Agent Collaboration for Scalable 3D Object Annotation
Jusheng Zhang, Yijia Fan, Zimo Wen +2
Driven by applications in autonomous driving robotics and augmented reality 3D object annotation presents challenges beyond 2D annotation including spatial complexity occlusion and…
FlashVLM: Text-Guided Visual Token Selection for Large Multimodal Models
Kaitong Cai, Jusheng Zhang, Jing Yang +4
Large vision-language models (VLMs) typically process hundreds or thousands of visual tokens per image or video frame, incurring quadratic attention cost and substantial redundancy…
LLM-CAS: Dynamic Neuron Perturbation for Real-Time Hallucination Correction
Jensen Zhang, Ningyuan Liu, Yijia Fan +5
Large language models (LLMs) often generate hallucinated content that lacks factual or contextual grounding, limiting their reliability in critical applications. Existing approache…
PTTA: A Pure Text-to-Animation Framework for High-Quality Creation
Ruiqi Chen, Kaitong Cai, Yijia Fan +1
Traditional animation production involves complex pipelines and significant manual labor cost. While recent video generation models such as Sora, Kling, and CogVideoX achieve impre…
MM-CoT:A Benchmark for Probing Visual Chain-of-Thought Reasoning in Multimodal Models
Jusheng Zhang, Kaitong Cai, Xiaoyang Guo +10
The ability to perform Chain-of-Thought (CoT) reasoning marks a major milestone for multimodal models (MMs), enabling them to solve complex visual reasoning problems. Yet a critica…
Hybrid Token Compression for Vision-Language Models
Jusheng Zhang, Xiaoyang Guo, Tongyu Mo +5
Vision-language models (VLMs) rely on hundreds of visual tokens, leading to high computational and memory costs. Existing compression methods face a trade-off: continuous compressi…
Causal Invariance and Counterfactual Learning Driven Cooperative Game for Multi-Label Classification
Yijia Fan, Jusheng Zhang, Kaitong Cai +2
Multi-label classification (MLC) remains vulnerable to label imbalance, spurious correlations, and distribution shifts, challenges that are particularly detrimental to rare label p…
3DAlign-DAER: Dynamic Attention Policy and Efficient Retrieval Strategy for Fine-grained 3D-Text Alignment at Scale
Yijia Fan, Jusheng Zhang, Kaitong Cai +3
Despite recent advancements in 3D-text cross-modal alignment, existing state-of-the-art methods still struggle to align fine-grained textual semantics with detailed geometric struc…
Cost-Effective Communication: An Auction-based Method for Language Agent Interaction
Yijia Fan, Jusheng Zhang, Kaitong Cai +4
Multi-agent systems (MAS) built on large language models (LLMs) often suffer from inefficient "free-for-all" communication, leading to exponential token costs and low signal-to-noi…
RaCoT: Plug-and-Play Contrastive Example Generation Mechanism for Enhanced LLM Reasoning Reliability
Kaitong Cai, Jusheng Zhang, Yijia Fan +2
Retrieval-Augmented Generation (RAG) faces a core bottleneck with knowledge-sparse and semantically ambiguous long-tail queries, where retrieval noise distorts reasoning and necess…
Agent-GSPO: Communication-Efficient Multi-Agent Systems via Group Sequence Policy Optimization
Yijia Fan, Jusheng Zhang, Jing Yang +1
To combat the prohibitive communication costs of ``free-for-all" multi-agent systems (MAS), we introduce \textbf{Agent-GSPO}, a framework that directly optimizes for token economy…
Backward-Friendly Optimization: Training Large Language Models with Approximate Gradients under Memory Constraints
Jing Yang, Kaitong Cai, Yijia Fan +2
Full fine-tuning of Large Language Models (LLMs) is notoriously memory-intensive, primarily because conventional optimizers such as SGD or Adam assume access to exact gradients der…
DrDiff: Dynamic Routing Diffusion with Hierarchical Attention for Breaking the Efficiency-Quality Trade-off
Jusheng Zhang, Yijia Fan, Kaitong Cai +5
This paper introduces DrDiff, a novel framework for long-text generation that overcomes the efficiency-quality trade-off through three core technologies. First, we design a dynamic…
MAT-Agent: Adaptive Multi-Agent Training Optimization
Jusheng Zhang, Kaitong Cai, Yijia Fan +2
Multi-label image classification demands adaptive training strategies to navigate complex, evolving visual-semantic landscapes, yet conventional methods rely on static configuratio…
OSC: Cognitive Orchestration through Dynamic Knowledge Alignment in Multi-Agent LLM Collaboration
Jusheng Zhang, Yijia Fan, Kaitong Cai +2
This paper introduces OSC (Orchestrating Cognitive Synergy), a knowledge-aware adaptive collaboration framework designed to enhance cognitive synergy in multi-agent systems with la…
CF-VLM:CounterFactual Vision-Language Fine-tuning
Jusheng Zhang, Kaitong Cai, Yijia Fan +2
Recent advances in vision-language models (VLMs) have greatly improved cross-modal semantic understanding, yet significant limitations remain in fine-grained discrimination and dee…