AI研究论文每日精选

xVerify: Efficient Answer Verifier for Reasoning Model Evaluations

Genius: A Generalizable and Purely Unsupervised Self-Training Framework For Advanced Reasoning

Seedream 3.0 Technical Report

How Instruction and Reasoning Data shape Post-Training: Data Quality through the Lens of Layer-wise Gradients

Heimdall: test-time scaling on the generative verification

Pixel-SAIL: Single Transformer For Pixel-Grounded Understanding

TextArena

Efficient Reasoning Models: A Survey

NormalCrafter: Learning Temporally Consistent Normals from Video Diffusion Priors

DataDecide: How to Predict Best Pretraining Data with Small Experiments

The Scalability of Simplicity: Empirical Analysis of Vision-Language Learning with a Single Transformer

A Minimalist Approach to LLM Reasoning: from Rejection Sampling to Reinforce

ReZero: Enhancing LLM search ability by trying one-more-time

Efficient Process Reward Model Training via Active Learning

SimpleAR: Pushing the Frontier of Autoregressive Visual Generation through Pretraining, SFT, and RL

Efficient Generative Model Training via Embedded Representation Warmup

D^2iT: Dynamic Diffusion Transformer for Accurate Image Generation

DeepMath-103K: A Large-Scale, Challenging, Decontaminated, and Verifiable Mathematical Dataset for Advancing Reasoning

RealHarm: A Collection of Real-World Language Model Application Failures

Efficient Hybrid Language Model Compression through Group-Aware SSM Pruning

VisualPuzzles: Decoupling Multimodal Reasoning Evaluation from Domain Knowledge

AI-University: An LLM-based platform for instructional alignment to scientific classrooms

PVUW 2025 Challenge Report: Advances in Pixel-level Understanding of Complex Videos in the Wild

Diffusion Distillation With Direct Preference Optimization For Efficient 3D LiDAR Scene Completion

Multimodal Long Video Modeling Based on Temporal Dynamic Context

LazyReview A Dataset for Uncovering Lazy Thinking in NLP Peer Reviews

Summarization of Multimodal Presentations with Vision-Language Models: Study of the Effect of Modalities and Structure

Adaptive Computation Pruning for the Forgetting Transformer

Aligning Generative Denoising with Discriminative Objectives Unleashes Diffusion for Visual Perception

Change State Space Models for Remote Sensing Change Detection