collaborators

7 papers

cs.CV2026

DeepSketcher: Internalizing Visual Manipulation for Multimodal Reasoning

Chi Zhang, Haibo Qiu, Qiming Zhang +3

The "thinking with images" paradigm represents a pivotal shift in the reasoning of Vision Language Models (VLMs), moving from text-dominant chain-of-thought to image-interactive re…

cs.LG2026

Metis-SPECS: Decoupling Multimodal Learning via Self-distilled Preference-based Cold Start

Kun Chen, Peng Shi, Haibo Qiu +4

Reinforcement learning (RL) with verifiable rewards has recently catalyzed a wave of "MLLM-r1" approaches that bring RL to vision language models. Most representative paradigms beg…

cs.CV2025

Learning When to Look: A Disentangled Curriculum for Strategic Perception in Multimodal Reasoning

Siqi Yang, Zilve Gao, Haibo Qiu +5

Multimodal Large Language Models (MLLMs) demonstrate significant potential but remain brittle in complex, long-chain visual reasoning tasks. A critical failure mode is "visual forg…

cs.CV2025

Counting Hallucinations in Diffusion Models

Shuai Fu, Jian Zhou, Qi Chen +7

Diffusion probabilistic models (DPMs) have demonstrated remarkable progress in generative tasks, such as image and video synthesis. However, they still often produce hallucinated s…

cs.CV2025

Perceptual-Evidence Anchored Reinforced Learning for Multimodal Reasoning

Chi Zhang, Haibo Qiu, Qiming Zhang +6

Reinforcement Learning with Verifiable Rewards (RLVR) has significantly advanced the reasoning capabilities of Large Language Models (LLMs) and is now being applied to Vision-Langu…

cs.CV2025

Towards Better & Faster Autoregressive Image Generation: From the Perspective of Entropy

Xiaoxiao Ma, Feng Zhao, Pengyang Ling +6

In this work, we first revisit the sampling issues in current autoregressive (AR) image generation models and identify that image tokens, unlike text tokens, exhibit lower informat…