activity
20242026
collaborators

25 papers

cs.CV2026

Residual Decoder Adapter: ID-Preserving Tokenizer Adaption for Autoregressive Text Rendering

Dongxing Mao, Jinpeng Wang, Jiahao Tang +6

Visual Autoregressive (AR) models generate images by predicting discrete tokens that are decoded by a visual tokenizer. Despite demonstrating strong overall image generation abilit…

cs.CV2026

FlowInOne:Unifying Multimodal Generation as Image-in, Image-out Flow Matching

Junchao Yi, Rui Zhao, Jiahao Tang +7

Multimodal generation has long been dominated by text-driven pipelines where language dictates vision but cannot reason or create within it. We challenge this paradigm by asking wh…

cs.CV2026

V-MAGE: A Game Evaluation Framework for Assessing Vision-Centric Capabilities in Multimodal Large Language Models

Xiangxi Zheng, Linjie Li, Zhengyuan Yang +5

Recent advancements in Multimodal Large Language Models (MLLMs) have demonstrated impressive capabilities in visual-text processing. However, existing static image-text benchmarks…

cs.LG2026

RAGEN-2: Reasoning Collapse in Agentic RL

Zihan Wang, Chi Gui, Xing Jin +13

RL training of multi-turn LLM agents is inherently unstable, and reasoning quality directly determines task performance. Entropy is widely used to track reasoning stability. Howeve…

cs.CV2026

EdiVal-Agent: An Object-Centric Framework for Automated, Fine-Grained Evaluation of Multi-Turn Editing

Tianyu Chen, Yasi Zhang, Zhi Zhang +13

Instruction-based image editing has advanced rapidly, yet reliable and interpretable evaluation remains a bottleneck. Current protocols either (i) depend on paired reference images…

cs.CL2026

STITCH: Simultaneous Thinking and Talking with Chunked Reasoning for Spoken Language Models

Cheng-Han Chiang, Xiaofei Wang, Linjie Li +7

Spoken Language Models (SLMs) are designed to take speech inputs and produce spoken responses. However, current SLMs lack the ability to perform an internal, unspoken thinking proc…