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 22

Submitted by

Elliott

Learning to Reason under Off-Policy Guidance

·
8 authors

4

Submitted by

cg1177

Eagle 2.5: Boosting Long-Context Post-Training for Frontier Vision-Language Models

·
21 authors

5

Submitted by

yueliu1999

FlowReasoner: Reinforcing Query-Level Meta-Agents

·
9 authors

2

Submitted by

emrecanacikgoz

ToolRL: Reward is All Tool Learning Needs

·
8 authors

2

Submitted by

Merlin-Hongru

OTC: Optimal Tool Calls via Reinforcement Learning

·
10 authors

Submitted by

salmannyu

X-Teaming: Multi-Turn Jailbreaks and Defenses with Adaptive Multi-Agents

·
10 authors

2

Submitted by

mpark

SphereDiff: Tuning-free Omnidirectional Panoramic Image and Video Generation via Spherical Latent Representation

·
5 authors

2

Submitted by

vyokky

UFO2: The Desktop AgentOS

·
21 authors

3

Submitted by

wchengad

StyleMe3D: Stylization with Disentangled Priors by Multiple Encoders on 3D Gaussians

·
10 authors

2

Submitted by

saxon

THOUGHTTERMINATOR: Benchmarking, Calibrating, and Mitigating Overthinking in Reasoning Models

·
4 authors

2

Submitted by

Ningyu

EasyEdit2: An Easy-to-use Steering Framework for Editing Large Language Models

·
10 authors

2

Submitted by

frog123123123123

Seeing from Another Perspective: Evaluating Multi-View Understanding in MLLMs

·
10 authors

Submitted by

Swtheking

LeetCodeDataset: A Temporal Dataset for Robust Evaluation and Efficient Training of Code LLMs

·
8 authors

2

Submitted by

ewrfcas

Uni3C: Unifying Precisely 3D-Enhanced Camera and Human Motion Controls for Video Generation

·
8 authors

Submitted by

pengxiang

InfiGUI-R1: Advancing Multimodal GUI Agents from Reactive Actors to Deliberative Reasoners

·
8 authors

2

Submitted by

Njb

DRAGON: Distributional Rewards Optimize Diffusion Generative Models

·
4 authors

2

Submitted by

Yuxiang007

LearnAct: Few-Shot Mobile GUI Agent with a Unified Demonstration Benchmark

·
9 authors

2

Submitted by

bys0318

An LMM for Efficient Video Understanding via Reinforced Compression of Video Cubes

·
7 authors

3

Submitted by

manuelkansy

LookingGlass: Generative Anamorphoses via Laplacian Pyramid Warping

·
5 authors

6

Submitted by

quyanh

RainbowPlus: Enhancing Adversarial Prompt Generation via Evolutionary Quality-Diversity Search

·
3 authors

8

Submitted by

lkeab

TAPIP3D: Tracking Any Point in Persistent 3D Geometry

·
4 authors

2

Submitted by

SieraL

NEMOTRON-CROSSTHINK: Scaling Self-Learning beyond Math Reasoning

·
11 authors

4

Submitted by

RanjanSapkota

RF-DETR Object Detection vs YOLOv12 : A Study of Transformer-based and CNN-based Architectures for Single-Class and Multi-Class Greenfruit Detection in Complex Orchard Environments Under Label Ambiguity

·
4 authors

2

Submitted by

reyavir

PROMPTEVALS: A Dataset of Assertions and Guardrails for Custom Production Large Language Model Pipelines

·
5 authors

2

Submitted by

nielsr

CoMotion: Concurrent Multi-person 3D Motion

·
5 authors

Submitted by

ChenWu98

Roll the dice & look before you leap: Going beyond the creative limits of next-token prediction

·
4 authors

Submitted by

nielsr

LoftUp: Learning a Coordinate-Based Feature Upsampler for Vision Foundation Models

·
5 authors

Submitted by

tnngo2

SilVar-Med: A Speech-Driven Visual Language Model for Explainable Abnormality Detection in Medical Imaging

·
6 authors

2