12 papers
PrecogUI: Proactive GUI Agents via Pre-cognitive Simulation and Experience Retrieval
Bin Kang, Jiarui Ouyang, Li Jiang +2
Existing reactive Graphical User Interface (GUI) agents often fail in long-horizon, dynamic scenarios, where unexpected disturbances trigger attention-diverting and cascading failu…
Scaling Multi-Reference Image Generation with Dynamic Reward Optimization
Wenwang Huang, Yusen Fu, Junjie Wang +6
While personalized image generation has achieved remarkable progress, multi-reference image generation (MRIG) remains a challenging task. Most existing benchmarks fail to adequatel…
Dynamic-dLLM: Dynamic Cache-Budget and Adaptive Parallel Decoding for Training-Free Acceleration of Diffusion LLM
Tianyi Wu, Xiaoxi Sun, Yanhua Jiao +5
Diffusion Large Language Models (dLLMs) offer a promising alternative to autoregressive models, excelling in text generation tasks due to their bidirectional attention mechanisms.…
Benchmarking and Evolving Reason-Reflect-Rectify for Reflective Visual Generation
Junjie Wang, Xinghua Lou, Jason Li +8
Text-to-Image (T2I) models and Unified Multimodal Models (UMMs) have achieved remarkable progress in visual generation. However, their reliance on a single-pass generation paradigm…
UniRefiner: Teaching Pre-trained ViTs to Self-Dispose Dross via Contrastive Register
Congpei Qiu, Zhaoyu Hu, Wei Ke +3
Representation learning with Vision Transformers (ViTs) has advanced rapidly, yet the utility of large-scale models in spatially sensitive tasks is hindered by spurious tokens. Pri…
AgentSteerTTS: A Multi-Agent Closed-Loop Framework for Composite-Instruction Text-to-Speech
Bin Kang, Shaoguo Wen, Yang Fan +6
While existing text-to-speech (TTS) models exhibit high expressiveness, fine-grained control over composite instructions remains challenging due to the structural mismatch between…
Efficient Reasoning with Balanced Thinking
Yulin Li, Tengyao Tu, Li Ding +5
Large Reasoning Models (LRMs) have shown remarkable reasoning capabilities, yet they often suffer from overthinking, expending redundant computational steps on simple problems, or…
Less Is More, but Where? Dynamic Token Compression via LLM-Guided Keyframe Prior
Yulin Li, Haokun Gui, Ziyang Fan +4
Recent advances in Video Large Language Models (VLLMs) have achieved remarkable video understanding capabilities, yet face critical efficiency bottlenecks due to quadratic computat…
CalibCLIP: Contextual Calibration of Dominant Semantics for Text-Driven Image Retrieval
Bin Kang, Bin Chen, Junjie Wang +3
Existing Visual Language Models (VLMs) suffer structural limitations where a few low contribution tokens may excessively capture global semantics, dominating the information aggreg…
Concerto: Joint 2D-3D Self-Supervised Learning Emerges Spatial Representations
Yujia Zhang, Xiaoyang Wu, Yixing Lao +4
Humans learn abstract concepts through multisensory synergy, and once formed, such representations can often be recalled from a single modality. Inspired by this principle, we intr…
Generalized Decoupled Learning for Enhancing Open-Vocabulary Dense Perception
Junjie Wang, Keyu Chen, Yulin Li +4
Dense visual perception tasks have been constrained by their reliance on predefined categories, limiting their applicability in real-world scenarios where visual concepts are unbou…
DeCLIP: Decoupled Learning for Open-Vocabulary Dense Perception
Junjie Wang, Bin Chen, Yulin Li +3
Dense visual prediction tasks have been constrained by their reliance on predefined categories, limiting their applicability in real-world scenarios where visual concepts are unbou…