Paper Reviews by AI

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.

VLMs self-improve with text-only training, outperforming vision for human-centered decisions, opening efficient enhancement avenues.

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.

TaoAvatar: Lifelike talking avatars in AR, using 3D Gaussian Splatting for real-time rendering and high fidelity.

Presents a strong baseline for multi-UAV tracking in thermal infrared video using YOLOv12 and BoT-SORT, achieving competitive results without complex enhancements.

PVChat: Personalize video understanding with one-shot learning, enabling identity-aware video comprehension.

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

OMG: optimized minimal 3D Gaussian splatting, enabling fast and efficient rendering with minimal storage.

OpenVLThinker: Iteratively refining vision-language models for complex reasoning, bridging the gap to R1-style capabilities.

This paper introduces deviation-factored post-training methods to enhance diversity and quality in creative LLM writing.

MARS: Optimizing prompts with multi-agent collaboration and Socratic learning for better LLM performance!

MAPS solves multimodal scientific problems better by combining multiple agents and Socratic learning.

LEMMA: LLMs learn math via mistake analysis and correction, boosting performance without external critics.

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

Gumbel-Softmax Flow Matching enables controllable biological sequence generation with straight-through guidance, scaling efficiently to high-dimensional simplices.

FFaceNeRF: Enables few-shot face editing in NeRFs via geometry adapter & latent mixing, enhancing control & quality with limited training data.

ETVA evaluates text-to-video alignment via fine-grained question generation and answering.

Zero-1-to-A: Animatable avatars from a single image using video diffusion, robust to spatial & temporal inconsistencies!