12 papers
SERO: Learning from Executable Oracle Continuations for Long-Horizon Agentic Reinforcement Learning
Dingyi Rong, Yue Shi, Chaofan Ma +5
Long-horizon agentic RL is constrained by the futures visited by the current policy. When rollouts fail to reach useful behaviors, improved credit assignment cannot provide supervi…
PixelIR: Fidelity-Perception Decoupling via Pixel-Space Image-Residual Flow Matching for Efficient One-Step Real-World Super-Resolution
Bingtian Qiao, Yue Shi, Yong Guo +2
Real-world image super-resolution (Real-ISR) aims to preserve structures supported by the degraded observation while reconstructing perceptually realistic details. However, existin…
H2R-Bench: Benchmarking Human-to-Robot Manipulation Video Generation in World Models
Dingyi Rong, Yue Shi, Chaofan Ma +6
Large-scale manipulation data is essential for robot learning, yet collecting robot demonstrations remains expensive and difficult to scale. Meanwhile, abundant egocentric human ma…
Robo2Process: Benchmarking and Learning Process-Aware Understanding in Vision-Language Robotic Manipulation
Dayu Xia, Yue Shi, Yao Mu +7
Vision-language models (VLMs) used as robotic critics, reward generators, and failure detectors must understand how manipulation unfolds, not only whether it succeeds. Yet fine-gra…
Efficient One-Step Diffusion Restoration Model with Compact Token Compression and Linear Attention
Bingtian Qiao, Yue Shi, Yingjie Zhou +3
Real-world image super-resolution aims to recover high-quality images from complex and unknown real-world degradations. However, existing generative Real-ISR methods largely inheri…
EchoPrune: Interpreting Redundancy as Temporal Echoes for Efficient VideoLLMs
Jiameng Li, Minye Wu, Jiezhang Cao +2
Long-form video understanding remains challenging for Video Large Language Models (VideoLLMs), as the dense frame sampling introduces massive visual tokens while sparse sampling ri…
EvalTalker: Learning to Evaluate Real-Portrait-Driven Multi-Subject Talking Humans
Yingjie Zhou, Xilei Zhu, Siyu Ren +11
Speech-driven Talking Human (TH) generation, commonly known as "Talker," currently faces limitations in multi-subject driving capabilities. Extending this paradigm to "Multi-Talker…
Who is a Better Player: LLM against LLM
Yingjie Zhou, Jiezhang Cao, Farong Wen +10
Adversarial board games, as a paradigmatic domain of strategic reasoning and intelligence, have long served as both a popular competitive activity and a benchmark for evaluating ar…
Who is a Better Talker: Subjective and Objective Quality Assessment for AI-Generated Talking Heads
Yingjie Zhou, Jiezhang Cao, Zicheng Zhang +6
Speech-driven methods for portraits are figuratively known as "Talkers" because of their capability to synthesize speaking mouth shapes and facial movements. Especially with the ra…
NTIRE 2025 XGC Quality Assessment Challenge: Methods and Results
Xiaohong Liu, Xiongkuo Min, Qiang Hu +92
This paper reports on the NTIRE 2025 XGC Quality Assessment Challenge, which will be held in conjunction with the New Trends in Image Restoration and Enhancement Workshop (NTIRE) a…
Q-Agent: Quality-Driven Chain-of-Thought Image Restoration Agent through Robust Multimodal Large Language Model
Yingjie Zhou, Jiezhang Cao, Farong Wen +7
Image restoration (IR) often faces various complex and unknown degradations in real-world scenarios, such as noise, blurring, compression artifacts, and low resolution, etc. Traini…
MEMO-Bench: A Multiple Benchmark for Text-to-Image and Multimodal Large Language Models on Human Emotion Analysis
Yingjie Zhou, Zicheng Zhang, Jiezhang Cao +6
Artificial Intelligence (AI) has demonstrated significant capabilities in various fields, and in areas such as human-computer interaction (HCI), embodied intelligence, and the desi…