Paper Reviews by AI

Video-T1 enhances video generation through test-time scaling, improving quality and consistency by viewing generation as a search for optimal video trajectories.

Video SimpleQA: A New Benchmark for Factuality Evaluation in Large Video Language Models.

CURA: Verbal process supervision improves coding agents.

Bottleneck Sampling: Accelerate diffusion models without retraining by cleverly using low-resolution priors for efficient inference!

MetaSpatial: RL for 3D Spatial Reasoning in VLMs

LLMs’ reasoning is decoded via sparse autoencoders, revealing key features that, when steered, enhance performance. First mechanistic account of reasoning in LLMs!

FFN Fusion: Parallelizing sequential computation in large language models for significant speedups!

Aligning image generation subtasks: Equivariant modeling boosts efficiency and generalization by leveraging natural visual signal invariance.

Diffusion-4K: Synthesizing ultra-high-resolution images with a new benchmark dataset and wavelet-based fine-tuning that makes 4K image creation more detailed and accessible!

CFG-Zero*: A better Classifier-Free Guidance to improve the image quality and text alignment in Flow Matching models.

Hummingbird: An efficient text-to-video model that balances quality and computational efficiency via pruning and visual feedback learning.

AlphaSpace enables robotic actions via semantic tokenization and symbolic reasoning, enhancing spatial intelligence in LLMs.

AETHER: a unified framework enabling geometry-aware reasoning in world models, achieving zero-shot generalization from synthetic to real-world data.

Vision-R1: Improves LVLMs via vision-guided reinforcement learning, eliminating the need for human feedback and specialized reward models.

OmnimatteZero: Real-time omnimatte using pre-trained video diffusion, no training needed!

LLMs falter on culturally adapted math problems, revealing a critical cultural bias.

AgentRxiv enables collaborative autonomous research via LLM agent preprint sharing, boosting performance and discovery.

RDTF: Efficient animated sticker generation via dual-mask training, outperforming parameter-efficient tuning under constrained resources.

Adaptive Diffusion Models with Minority-Aware Adaptive DPO

V-SEEK accelerates LLM reasoning on open-hardware RISC-V platforms, achieving up to 3.0x speedup through optimized kernels and memory management.