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

Mar 10

Submitted by

mozhu

Lost in Stories: Consistency Bugs in Long Story Generation by LLMs

·
6 authors

Submitted by

lifuguan

Holi-Spatial: Evolving Video Streams into Holistic 3D Spatial Intelligence

·
17 authors

Submitted by

Junyi42

LoGeR: Long-Context Geometric Reconstruction with Hybrid Memory

deepmind

Submitted by

yxizhong

Believe Your Model: Distribution-Guided Confidence Calibration

·
4 authors

2

Submitted by

hbx

How Far Can Unsupervised RLVR Scale LLM Training?

·
21 authors

Submitted by

WANGAndyYucheng

CARE-Edit: Condition-Aware Routing of Experts for Contextual Image Editing

·
5 authors

Submitted by

mickyhimself

CoCo: Code as CoT for Text-to-Image Preview and Rare Concept Generation

·
13 authors

Submitted by

zhengli1013

HiAR: Efficient Autoregressive Long Video Generation via Hierarchical Denoising

·
6 authors

Submitted by

jacklanda

\$OneMillion-Bench: How Far are Language Agents from Human Experts?

bigai

Beijing Institute for General Artificial Intelligence

Submitted by

Avihu

NLE: Non-autoregressive LLM-based ASR by Transcript Editing

ibm

Submitted by

Luo-Yihong

TDM-R1: Reinforcing Few-Step Diffusion Models with Non-Differentiable Reward

Submitted by

akshaynambi

Scaling Agentic Capabilities, Not Context: Efficient Reinforcement Finetuning for Large Toolspaces

MicrosoftResearch

Microsoft Research

Submitted by

Yoniel

Concept-Guided Fine-Tuning: Steering ViTs away from Spurious Correlations to Improve Robustness

·
3 authors

Submitted by

apeters

Unlocking Data Value in Finance: A Study on Distillation and Difficulty-Aware Training

OpenDataArena

Submitted by

Yuxiang007

PIRA-Bench: A Transition from Reactive GUI Agents to GUI-based Proactive Intent Recommendation Agents

·
5 authors

1

Submitted by

Dennis314

Training-free Latent Inter-Frame Pruning with Attention Recovery

UTEXAS

University of Texas at Austin

2

Submitted by

ChaosLiao

PureCC: Pure Learning for Text-to-Image Concept Customization

KlingTeam

Submitted by

Antimage01

From Narrow to Panoramic Vision: Attention-Guided Cold-Start Reshapes Multimodal Reasoning

Qwen

Submitted by

BibbyResearch

AutoResearch-RL: Perpetual Self-Evaluating Reinforcement Learning Agents for Autonomous Neural Architecture Discovery

Anthropic

Submitted by

taesiri

Scale Space Diffusion

·
3 authors

Submitted by

taesiri

Agentic Critical Training

·
6 authors

Submitted by

JREion

FVG-PT: Adaptive Foreground View-Guided Prompt Tuning for Vision-Language Models

uts-research

University of Technology Sydney

Submitted by

Row11n

CaTok: Taming Mean Flows for One-Dimensional Causal Image Tokenization

ShareLab-SII

Submitted by

PardisTaghavi

NaviDriveVLM: Decoupling High-Level Reasoning and Motion Planning for Autonomous Driving

TexasAMUniversity

Texas A&M University

Submitted by

bdqnghi

Building AI Coding Agents for the Terminal: Scaffolding, Harness, Context Engineering, and Lessons Learned

·
1 authors

Submitted by

taesiri

OfficeQA Pro: An Enterprise Benchmark for End-to-End Grounded Reasoning

databricks

Submitted by

ZongqianLi

Scaling Data Difficulty: Improving Coding Models via Reinforcement Learning on Fresh and Challenging Problems

MicrosoftResearch

Microsoft Research

Submitted by

ZongqianLi

Breaking Training Bottlenecks: Effective and Stable Reinforcement Learning for Coding Models

MicrosoftResearch

Microsoft Research

Submitted by

RaghavvGoel

Skip to the Good Part: Representation Structure & Inference-Time Layer Skipping in Diffusion vs. Autoregressive LLMs

qualcomm

Submitted by

rcfeng

HY-WU (Part I): An Extensible Functional Neural Memory Framework and An Instantiation in Text-Guided Image Editing

Tencent-Hunyuan

Tencent Hunyuan

Submitted by

menghao22

Making LLMs Optimize Multi-Scenario CUDA Kernels Like Experts

·
5 authors

1

Submitted by

Franck-Dernoncourt

Agentic Planning with Reasoning for Image Styling via Offline RL

·
6 authors

Submitted by

ACID23333

Sparse-BitNet: 1.58-bit LLMs are Naturally Friendly to Semi-Structured Sparsity

MicrosoftResearch

Microsoft Research

Submitted by

yongers

Generalizable Knowledge Distillation from Vision Foundation Models for Semantic Segmentation

·
7 authors

Submitted by

jayjunlee

HydroShear: Hydroelastic Shear Simulation for Tactile Sim-to-Real Reinforcement Learning

·
7 authors

Submitted by

Duke-de-Artois

SlowBA: An efficiency backdoor attack towards VLM-based GUI agents

·
5 authors

Submitted by

menghao22

PresentBench: A Fine-Grained Rubric-Based Benchmark for Slide Generation

·
6 authors

Submitted by

phamtrongthang

MedSteer: Counterfactual Endoscopic Synthesis via Training-Free Activation Steering

·
5 authors

Submitted by

olaflaitinen

Spatiotemporal Heterogeneity of AI-Driven Traffic Flow Patterns and Land Use Interaction: A GeoAI-Based Analysis of Multimodal Urban Mobility

·
1 authors

1

Submitted by

ljx1002

TAPFormer: Robust Arbitrary Point Tracking via Transient Asynchronous Fusion of Frames and Events

·
7 authors

Submitted by

PardisTaghavi

Autophoresis of a Janus particle near a planar wall: a lubrication limit

·
3 authors

Submitted by

SteveZeyuZhang

MWM: Mobile World Models for Action-Conditioned Consistent Prediction

PekingUniversity

Peking University

Submitted by

difra00

Retrieval-Augmented Generation for Predicting Cellular Responses to Gene Perturbation

Sapienza

Sapienza University of Rome

Submitted by

zhouyuxuanyx

SeedPolicy: Horizon Scaling via Self-Evolving Diffusion Policy for Robot Manipulation

·
7 authors

1