2025-03-28s

Model Merging: An unlearning system, which combines specialized models, achieves top results in SemEval-2025 Task 4 by selectively erasing sensitive knowledge.

Video-R1: First to explore rule-based RL for video reasoning in MLLMs, enhancing performance on key benchmarks.

VBench 2.0: A new benchmark suite advancing video generation evaluation with intrinsic faithfulness metrics.

UI-R1 enhances GUI agents’ action prediction using reinforcement learning.

ResearchBench: Benchmarking LLMs for Scientific Discovery via Inspiration-Based Task Decomposition.

ReaRAG enhances factuality in large reasoning models (LRMs) by integrating knowledge-guided reasoning with iterative retrieval augmented generation.

Optimal Stepsize Distillation accelerates diffusion sampling by distilling knowledge from reference trajectories, achieving 10x speedup with minimal performance loss.

Lumina-Image 2.0: A unified & efficient image generative framework, outperforming previous models with only 2.6B parameters.

LOCATEdit refines cross-attention maps with graph Laplacian regularization, achieving precise & localized text-guided image editing without artifacts.

LeX-Art: High-quality text-to-image generation via scalable data synthesis.

This survey presents a methodology-centered taxonomy of LLM agent systems, linking design principles to emergent behaviors and identifying future research directions.

This survey explores the evolution of physics cognition in video generation, addressing the gap between visual realism and physical accuracy.

Embodied-Reasoner: Integrates visual search, reasoning, and action for interactive tasks, outperforming existing models in embodied environments.

ChatAnyone: Stylized real-time portrait video generation with hierarchical motion diffusion model.

OlymMATH: A new Olympiad-level math benchmark rigorously tests LLMs’ reasoning, revealing limitations and paving the way for advancements.

UniDisc: a unified multimodal discrete diffusion model for joint text and image generation, surpassing autoregressive models in quality & efficiency!

Synthetic data can enhance the physical realism of video synthesis, paving the way for more believable generated content.

FINAUDIO: First benchmark for financial audio LLMs, enhancing financial audio analysis and investment decisions.

Feature4X: 4D Agentic AI from Monocular Video w/ Gaussian Feature Fields