2025-03-27s

VILBENCH: Vision-Language Process Reward Modeling Suite

Fixing fine-tuned diffusion models! By using richer, unconditional priors, they generate better images and videos.

Open Deep Search (ODS): Democratizing Search with Open-source Reasoning Agents.

MCTS-RAG: Combines Monte Carlo Tree Search with Retrieval-Augmented Generation to enhance small LMs’ reasoning on complex tasks.

DINeMo: Learns 3D models with no 3D annotations, leveraging pseudo-correspondence from visual foundation models for enhanced pose estimation.

BIZGEN: Article-level Visual Text Rendering for Infographics Generation

LongTextAR advances long-text image generation via a novel tokenizer, enabling accurate, controllable, and high-fidelity text rendering in images.

ADS-Edit: Empowering autonomous driving with multimodal knowledge editing!

Opt-CWM: Self-supervised motion learning via counterfactual optimization, achieving state-of-the-art without labels!

LogQuant: 2-bit quantization for KV cache, superior accuracy!

MLLMs still struggle with spatial reasoning! LEGO-Puzzles benchmark reveals critical deficiencies, paving the way for AI advancement.

Visually perfect generations aren’t always optimal! GenHancer finds that subtly imperfect generations can greatly improve vision-centric tasks.

Dita: Scales a diffusion transformer for generalist robot policies, enabling 10-shot learning in complex, real-world tasks.

Attention-IoU reveals model biases by analyzing attention maps, offering insights beyond dataset labels and improving debiasing techniques.

AccVideo accelerates video diffusion by 8.5x with a synthetic dataset and trajectory-based distillation, maintaining quality and enabling higher resolution video generation.

PathoHR: Boost breast cancer survival prediction with high-resolution pathology images!

Motion blur, usually a problem, is now a solution! This paper estimates camera motion from motion-blurred images, acting like an IMU.