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

May 16

Submitted by

zhiyuanhucs

Beyond 'Aha!': Toward Systematic Meta-Abilities Alignment in Large Reasoning Models

·
8 authors

3

Submitted by

jinheon

System Prompt Optimization with Meta-Learning

·
3 authors

3

Submitted by

SiyuanH

EnerVerse-AC: Envisioning Embodied Environments with Action Condition

·
11 authors

Submitted by

nielsr

Parallel Scaling Law for Language Models

·
8 authors

Submitted by

Seongyun

The CoT Encyclopedia: Analyzing, Predicting, and Controlling how a Reasoning Model will Think

·
12 authors

2

Submitted by

SiyuanH

EWMBench: Evaluating Scene, Motion, and Semantic Quality in Embodied World Models

·
8 authors

Submitted by

ryanzhangfan

End-to-End Vision Tokenizer Tuning

·
8 authors

3

Submitted by

Tigerph

WorldPM: Scaling Human Preference Modeling

·
20 authors

Submitted by

Jerrycool

MLE-Dojo: Interactive Environments for Empowering LLM Agents in Machine Learning Engineering

·
11 authors

2

Submitted by

stefanvasilev

Unilogit: Robust Machine Unlearning for LLMs Using Uniform-Target Self-Distillation

·
6 authors

2

Submitted by

swarnaNLP

J1: Incentivizing Thinking in LLM-as-a-Judge via Reinforcement Learning

·
7 authors

Submitted by

Jiafei1224

PointArena: Probing Multimodal Grounding Through Language-Guided Pointing

·
15 authors

Submitted by

ZehanWang

Depth Anything with Any Prior

·
7 authors

Submitted by

intchous

Style Customization of Text-to-Vector Generation with Image Diffusion Priors

·
3 authors

3

Submitted by

adarshxs

Achieving Tokenizer Flexibility in Language Models through Heuristic Adaptation and Supertoken Learning

·
4 authors

2

Submitted by

Warrieryes

OpenThinkIMG: Learning to Think with Images via Visual Tool Reinforcement Learning

·
11 authors

3

Submitted by

HeverLaw

ReSurgSAM2: Referring Segment Anything in Surgical Video via Credible Long-term Tracking

·
7 authors

2

Submitted by

yenchic

3D-Fixup: Advancing Photo Editing with 3D Priors

·
8 authors

2

Submitted by

AlignAI

QuXAI: Explainers for Hybrid Quantum Machine Learning Models

·
6 authors

3

Submitted by

sayakpaul

Exploring the Deep Fusion of Large Language Models and Diffusion Transformers for Text-to-Image Synthesis

·
5 authors

2

Submitted by

csgaobb

AdaptCLIP: Adapting CLIP for Universal Visual Anomaly Detection

·
10 authors

4

Submitted by

csgaobb

MetaUAS: Universal Anomaly Segmentation with One-Prompt Meta-Learning

·
1 authors

2

Submitted by

csgaobb

Learning to Detect Multi-class Anomalies with Just One Normal Image Prompt

·
1 authors

2

Submitted by

csgaobb

Few-Shot Anomaly-Driven Generation for Anomaly Classification and Segmentation

·
5 authors

2

Submitted by

RanjanSapkota

AI Agents vs. Agentic AI: A Conceptual Taxonomy, Applications and Challenge

·
3 authors

2

Submitted by

mlfu7

Real2Render2Real: Scaling Robot Data Without Dynamics Simulation or Robot Hardware

·
8 authors

Submitted by

prithwishdan

X-Sim: Cross-Embodiment Learning via Real-to-Sim-to-Real

·
7 authors