activity
20242026
collaborators

8 papers

cs.CV2026

AVA-Encoder: Towards Agent-Native Video Representation Learning

Chuyue Li, Jinpeng Yu, Haozhe Wang +8

Video creative agents still lack an effective way to learn from high-quality human films, limiting their ability to produce cinematic-grade videos. A key challenge is the absence o…

cs.CV2026

What to Edit Next: Visually Aligned Image-Editing Follow-Up Suggestions in Conversational Systems

Zhijing Zhang, Jinpeng Yu, Xin Song +6

Conversational assistants increasingly recommend follow-up edits to help users continue a task. Existing systems primarily target text-only interactions, leaving image-creation con…

cs.CV2026

Rethinking Classifier-Free Guidance in On-Policy Diffusion Distillation

Bingnan Li, Haozhe Wang, Haozhong Xiong +5

On-policy distillation (OPD) adapts diffusion models by querying a teacher along trajectories generated by the current student, but how it should behave under classifier-free guida…

cs.CL2026

DLLG: Dynamic Logit-Level Gating of LLM Experts

Bingnan Li, Zhaoyang Zhang, Xiaoze Liu +6

Leveraging multiple specialized LLMs can combine complementary strengths, but existing approaches trade adaptability for stability: routing commits prematurely, heuristic ensemblin…

cs.CV2026

CyCLeGen: Cycle-Consistent Layout Prediction and Image Generation in Vision Foundation Models

Xiaojun Shan, Haoyu Shen, Yucheng Mao +5

We present CyCLeGen, a unified vision-language foundation model capable of both image understanding and image generation within a single autoregressive framework. Unlike existing v…

cs.CV2025

OverLayBench: A Benchmark for Layout-to-Image Generation with Dense Overlaps

Bingnan Li, Chen-Yu Wang, Haiyang Xu +7

Despite steady progress in layout-to-image generation, current methods still struggle with layouts containing significant overlap between bounding boxes. We identify two primary ch…