new

Get trending papers in your email inbox once a day!

Get trending papers in your email inbox!

Daily Papers

byAK and the research community

Apr 16

Submitted by

Hush-cd

xVerify: Efficient Answer Verifier for Reasoning Model Evaluations

·
9 authors

2

Submitted by

xufangzhi

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

·
9 authors

2

Submitted by

BestWishYsh

Seedream 3.0 Technical Report

·
31 authors

Submitted by

zhoutianyi

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

·
4 authors

2

Submitted by

WesleyShi

Heimdall: test-time scaling on the generative verification

·
2 authors

2

Submitted by

LXT

Pixel-SAIL: Single Transformer For Pixel-Grounded Understanding

·
9 authors

3

Submitted by

Benjamin-eecs

TextArena

·
6 authors

3

Submitted by

FSCCS

Efficient Reasoning Models: A Survey

·
4 authors

4

Submitted by

wbhu-tc

NormalCrafter: Learning Temporally Consistent Normals from Video Diffusion Priors

·
5 authors

2

Submitted by

IanMagnusson

DataDecide: How to Predict Best Pretraining Data with Small Experiments

·
13 authors

Submitted by

LXT

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

·
7 authors

3

Submitted by

weqweasdas

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

·
11 authors

Submitted by

alandao

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

·
2 authors

2

Submitted by

dreamerdeo

Efficient Process Reward Model Training via Active Learning

·
8 authors

2

Submitted by

Daniel0724

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

·
7 authors

Submitted by

SempraETY

Efficient Generative Model Training via Embedded Representation Warmup

·
4 authors

2

Submitted by

CoreloneH

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

·
5 authors

Submitted by

davanstrien

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

·
15 authors

Submitted by

pierlj

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

·
4 authors

3

Submitted by

jrd971000

Efficient Hybrid Language Model Compression through Group-Aware SSM Pruning

·
18 authors

Submitted by

yueqis

VisualPuzzles: Decoupling Multimodal Reasoning Evaluation from Domain Knowledge

·
6 authors

2

Submitted by

simocimolato

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

·
8 authors

2

Submitted by

HenghuiDing

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

·
36 authors

2

Submitted by

SYZhang0805

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

·
8 authors

Submitted by

Hoar012

Multimodal Long Video Modeling Based on Temporal Dynamic Context

·
4 authors

2

Submitted by

sukannya

LazyReview A Dataset for Uncovering Lazy Thinking in NLP Peer Reviews

·
5 authors

2

Submitted by

gigant

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

·
3 authors

2

Submitted by

zhixuan-lin

Adaptive Computation Pruning for the Forgetting Transformer

·
4 authors

2

Submitted by

ziqipang

Aligning Generative Denoising with Discriminative Objectives Unleashes Diffusion for Visual Perception

·
3 authors

2

Submitted by

ElmanGhazaei

Change State Space Models for Remote Sensing Change Detection

·
2 authors

2