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 20

Submitted by

KaitaoSong

Chain-of-Model Learning for Language Model

·
17 authors

2

Submitted by

NeoZ123

AdaptThink: Reasoning Models Can Learn When to Think

·
5 authors

1

Submitted by

Swtheking

AdaCoT: Pareto-Optimal Adaptive Chain-of-Thought Triggering via Reinforcement Learning

·
9 authors

1

Submitted by

gmlwns5176

Delta Attention: Fast and Accurate Sparse Attention Inference by Delta Correction

·
3 authors

1

Submitted by

tianbaoxiexxx

Scaling Computer-Use Grounding via User Interface Decomposition and Synthesis

·
15 authors

2

Submitted by

PY007

Faster Video Diffusion with Trainable Sparse Attention

·
8 authors

1

Submitted by

Vinnnf

Thinkless: LLM Learns When to Think

·
3 authors

1

Submitted by

Wa2erGo

Model Merging in Pre-training of Large Language Models

·
24 authors

Submitted by

zlzheng

Seek in the Dark: Reasoning via Test-Time Instance-Level Policy Gradient in Latent Space

·
11 authors

3

Submitted by

Cierra0506

MM-PRM: Enhancing Multimodal Mathematical Reasoning with Scalable Step-Level Supervision

·
7 authors

1

Submitted by

ohseungjun

Hybrid 3D-4D Gaussian Splatting for Fast Dynamic Scene Representation

·
4 authors

1

Submitted by

Sangsang

FedSVD: Adaptive Orthogonalization for Private Federated Learning with LoRA

·
8 authors

2

Submitted by

Zkkkai

CPGD: Toward Stable Rule-based Reinforcement Learning for Language Models

·
7 authors

1

Submitted by

yuhuixu

Fractured Chain-of-Thought Reasoning

·
7 authors

1

Submitted by

lytang

ChartMuseum: Testing Visual Reasoning Capabilities of Large Vision-Language Models

·
15 authors

2

Submitted by

lixiaoxi45

Neuro-Symbolic Query Compiler

·
8 authors

2

Submitted by

Dreamer312

SEED-GRPO: Semantic Entropy Enhanced GRPO for Uncertainty-Aware Policy Optimization

·
4 authors

2

Submitted by

zszhong

VisionReasoner: Unified Visual Perception and Reasoning via Reinforcement Learning

·
7 authors

1

Submitted by

Vasily

Through the Looking Glass: Common Sense Consistency Evaluation of Weird Images

·
6 authors

2

Submitted by

merlerm

ViPlan: A Benchmark for Visual Planning with Symbolic Predicates and Vision-Language Models

·
8 authors

1

Submitted by

amphora

When AI Co-Scientists Fail: SPOT-a Benchmark for Automated Verification of Scientific Research

·
11 authors

1

Submitted by

Doreamonzzz

Accelerate TarFlow Sampling with GS-Jacobi Iteration

·
2 authors

Submitted by

Tyrannosaurus

EfficientLLM: Efficiency in Large Language Models

·
16 authors

Submitted by

gentaiscool

R3: Robust Rubric-Agnostic Reward Models

·
8 authors

Submitted by

vincentkoc

Tiny QA Benchmark++: Ultra-Lightweight, Synthetic Multilingual Dataset Generation & Smoke-Tests for Continuous LLM Evaluation

·
1 authors

2

Submitted by

Harold328

FinePhys: Fine-grained Human Action Generation by Explicitly Incorporating Physical Laws for Effective Skeletal Guidance

·
6 authors

1

Submitted by

yanboding

MTVCrafter: 4D Motion Tokenization for Open-World Human Image Animation

·
4 authors

1

Submitted by

Paulmzr

Efficient Speech Language Modeling via Energy Distance in Continuous Latent Space

·
6 authors

Submitted by

Krystalan

ExTrans: Multilingual Deep Reasoning Translation via Exemplar-Enhanced Reinforcement Learning

·
3 authors

1

Submitted by

mgvz

HISTAI: An Open-Source, Large-Scale Whole Slide Image Dataset for Computational Pathology

·
3 authors

1

Submitted by

Harahan

QVGen: Pushing the Limit of Quantized Video Generative Models

·
7 authors

1

Submitted by

xuyige

SoftCoT++: Test-Time Scaling with Soft Chain-of-Thought Reasoning

·
4 authors

1

Submitted by

Ksgk-fy

From Grunts to Grammar: Emergent Language from Cooperative Foraging

·
7 authors

Submitted by

minwoosun

MedCaseReasoning: Evaluating and learning diagnostic reasoning from clinical case reports

·
10 authors

1

Submitted by

zhilinw

HelpSteer3-Preference: Open Human-Annotated Preference Data across Diverse Tasks and Languages

·
9 authors

1

Submitted by

AndreiArhire

Learned Lightweight Smartphone ISP with Unpaired Data

·
2 authors

1

Submitted by

JitaiHao

A Token is Worth over 1,000 Tokens: Efficient Knowledge Distillation through Low-Rank Clone

·
6 authors

1

Submitted by

PChemGuy

LLM Context Conditioning and PWP Prompting for Multimodal Validation of Chemical Formulas

·
1 authors

1

Submitted by

lekssays

TechniqueRAG: Retrieval Augmented Generation for Adversarial Technique Annotation in Cyber Threat Intelligence Text

·
4 authors

1

Submitted by

oshaikh13

Creating General User Models from Computer Use

·
7 authors

Submitted by

PChemGuy

AI-Driven Scholarly Peer Review via Persistent Workflow Prompting, Meta-Prompting, and Meta-Reasoning

·
1 authors

1

Submitted by

MahtaFetrat

Fast, Not Fancy: Rethinking G2P with Rich Data and Rule-Based Models

·
3 authors

Submitted by

dnoever

Can AI Freelancers Compete? Benchmarking Earnings, Reliability, and Task Success at Scale

·
2 authors