Latest Papers

CodeDiffuser: Attention-Enhanced Diffusion Policy via VLM-Generated Code for Instruction Ambiguity

Optimizing Multilingual Text-To-Speech with Accents & Emotions

Hunyuan-GameCraft: High-dynamic Interactive Game Video Generation with Hybrid History Condition

VIKI-R: Coordinating Embodied Multi-Agent Cooperation via Reinforcement Learning

PAROAttention: Pattern-Aware ReOrdering for Efficient Sparse and Quantized Attention in Visual Generation Models

Vision-Guided Chunking Is All You Need: Enhancing RAG with Multimodal Document Understanding

Drag-and-Drop LLMs: Zero-Shot Prompt-to-Weights

Evolutionary Caching to Accelerate Your Off-the-Shelf Diffusion Model

RE-IMAGINE: Symbolic Benchmark Synthesis for Reasoning Evaluation

SonicVerse: Multi-Task Learning for Music Feature-Informed Captioning