🏢 Hong Kong University of Science and Technology

Interactive Generative Video (IGV) can revolutionize game creation by using AI to generate endless, novel content for next-gen game engines.

FluxFlow: Make your video generator stronger via temporal regularization!

Rewards Are Enough!

LVAS-Agent: Multi-agent system conquers long-video audio synthesis with collaborative dubbing, script, design, & more!

LightGen: Efficient image generation via knowledge distillation and direct preference optimization.

TDM: a new diffusion distillation paradigm unifying trajectory distillation and distribution matching, surpassing teachers in a data-free manner with state-of-the-art performance and low training cost…

RectifiedHR: Enables training-free high-resolution image generation via energy rectification, boosting both efficiency and effectiveness.

GOAT: Adaptively boosts LoRA with SVD & MoE alignment, closing the gap with Full FT.

Perovskite-LLM: a new knowledge-enhanced system boosts perovskite solar cell research by integrating a domain-specific knowledge graph, high-quality datasets, and specialized LLMs for superior knowled…

mmMamba: a novel framework creates linear-complexity multimodal models via distillation, drastically improving efficiency without sacrificing performance.

Atom of Thoughts (AOT) revolutionizes LLM test-time scaling by decomposing complex reasoning into independent sub-questions, drastically reducing computation while maintaining high accuracy.

FinMTEB: A new benchmark reveals that general-purpose embedding models struggle in the finance domain; domain-specific models excel, and surprisingly, simple BoW outperforms sophisticated models on ce…

ThinkDiff empowers text-to-image diffusion models with multimodal reasoning by aligning vision-language models to an LLM decoder, achieving state-of-the-art results on in-context reasoning benchmarks.

CODEI/O: Condensing reasoning patterns from code into LLM training data for enhanced reasoning.

CustomVideoX: Zero-shot personalized video generation, exceeding existing methods in quality & consistency via 3D reference attention and dynamic adaptation.

LLMs excel at complex reasoning but struggle with planning; this paper introduces a test-time scaling approach that enhances LLMs’ PDDL reasoning, enabling high-quality PDDL domain generation, outperf…

FlashVideo: Generate stunning high-resolution videos efficiently using a two-stage framework prioritizing fidelity and detail, achieving state-of-the-art results.

Llasa, a novel single-Transformer TTS model, achieves state-of-the-art performance by scaling both training and inference compute, improving naturalness, prosody and emotional expressiveness.

W2SD: A novel framework boosts diffusion model quality by using the difference between weak and strong models to refine sampling trajectories, achieving state-of-the-art performance.

GaussianAvatar-Editor enables photorealistic, text-driven editing of animatable 3D heads, solving motion occlusion and ensuring temporal consistency.