14 papers
Do Video Generators Track the World Across Segments? A Benchmark and Method for World-State Reasoning in Video Continuation
Yingmao Miao, Pengfei Zhang, Chaoran Xu +5
Video generators build long videos by composing shorter parts, either by generating segments one after another or by autoregressively extending chunks. Each new part usually depend…
SCOPE: Subspace Clustering with Online Per-Head Top-K Estimation for Sparse Video Attention
Qi Zhao, Qirui Li, Hanlin Tang +10
Diffusion Transformers (DiTs) incur quadratic self-attention cost over spatiotemporal tokens. Existing training-free sparse attention methods often construct sparse masks from bloc…
Text Template Tokens Are Implicit Semantic Registers in Diffusion Transformers
Maohua Li, Qirui Li, Yanke Zhou +10
Modern text-to-image diffusion transformers (DiTs) generate images through joint attention, in which text and image tokens interact directly within a single sequence. In large-scal…
Beyond Time Shifts: Adapting Omni-LLM as a Reference-Free Evaluator for Generative Audio-Visual Models
Yijie Qian, Juncheng Wang, Chao Xu +6
As audio-visual generative models evolve into world simulators, cross-modal synchronization stands as a critical proxy for assessing the consistency of world dynamics and causality…
Rethinking Cross-Layer Information Routing in Diffusion Transformers
Chao Xu, Maohua Li, Qirui Li +9
Diffusion Transformers (DiTs) have become a de facto backbone of modern visual generation, and nearly every major axis of their design -- tokenization, attention, conditioning, obj…
RISE: Reliable Improvement in Self-Evolving Vision-Language Models
Chaoran Xu, Yingmao Miao, Pengfei Zhang +3
Vision-language models (VLMs) have achieved strong multimodal reasoning capabilities, but further improving them still relies heavily on large-scale human-constructed supervision f…
Creative Quality Alignment: Expert Tacit Knowledge Transfer via Chain-of-Thought Fine-Tuning
Bo Zou, Chao Xu
This paper provides an empirical implementation of the creative quality metric proposed in Calibrated Surprise (Zou & Xu, 2026a). The question this paper addresses is: does this ma…
QUIET: A Multi-Blank Cascaded Story Cloze Benchmark for LLM Creative Generation Capability
Bo Zou, Chao Xu
Large language models (LLMs) face a dual challenge in creative capability evaluation: existing benchmarks (e.g., Story Cloze Test, HellaSwag) measure models' discriminative ability…
BC Protocol: Structured Dual-Expert Dialogue for Eliciting High-Quality Chain-of-Thought Post-Training Data
Bo Zou, Chao Xu
High-quality expert chain-of-thought (CoT) data is one of the core bottlenecks in large language model (LLM) post-training. Existing data production methods each have structural li…
NEWTON: Agentic Planning for Physically Grounded Video Generation
Yuxiang Feng, Juncheng Wang, Chao Xu +7
Video generation models produce visually compelling results but systematically violate physical commonsense -- on VideoPhy-2, the best model achieves only 32.6% joint accuracy. We…
AcceRL: A Distributed Asynchronous Reinforcement Learning and World Model Framework for Vision-Language-Action Models
Chengxuan Lu, Shukuan Wang, Yanjie Li +10
Reinforcement learning (RL) for large-scale Vision-Language-Action (VLA) models is severely bottlenecked by synchronization barriers and the high cost of environment data acquisiti…
Guided by the Plan: Enhancing Faithful Autoregressive Text-to-Audio Generation with Guided Decoding
Juncheng Wang, Zhe Hu, Chao Xu +5
Autoregressive (AR) models excel at generating temporally coherent audio by producing tokens sequentially, yet they often falter in faithfully following complex textual prompts, es…
Language Model Based Text-to-Audio Generation: Anti-Causally Aligned Collaborative Residual Transformers
Juncheng Wang, Chao Xu, Cheng Yu +5
While language models (LMs) paired with residual vector quantization (RVQ) tokenizers have shown promise in text-to-audio (T2A) generation, they still lag behind diffusion-based mo…
Synchronized Video-to-Audio Generation via Mel Quantization-Continuum Decomposition
Juncheng Wang, Chao Xu, Cheng Yu +4
Video-to-audio generation is essential for synthesizing realistic audio tracks that synchronize effectively with silent videos. Following the perspective of extracting essential si…