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

Aug 21

Submitted by

taesiri

DuPO: Enabling Reliable LLM Self-Verification via Dual Preference Optimization

·
10 authors

Submitted by

ElsaShaw

From Scores to Skills: A Cognitive Diagnosis Framework for Evaluating Financial Large Language Models

·
11 authors

Submitted by

liujiashuo77

FutureX: An Advanced Live Benchmark for LLM Agents in Future Prediction

·
30 authors

3

Submitted by

ZhaoyangLyu

MeshCoder: LLM-Powered Structured Mesh Code Generation from Point Clouds

·
12 authors

Submitted by

Canyu

Tinker: Diffusion's Gift to 3D--Multi-View Consistent Editing From Sparse Inputs without Per-Scene Optimization

·
6 authors

Submitted by

Wyattz23

From AI for Science to Agentic Science: A Survey on Autonomous Scientific Discovery

·
22 authors

Submitted by

Ziyang

MCP-Universe: Benchmarking Large Language Models with Real-World Model Context Protocol Servers

·
10 authors

Submitted by

taesiri

NVIDIA Nemotron Nano 2: An Accurate and Efficient Hybrid Mamba-Transformer Reasoning Model

·
211 authors

3

Submitted by

Felix1023

Quantization Meets dLLMs: A Systematic Study of Post-training Quantization for Diffusion LLMs

·
9 authors

2

Submitted by

CircleRadon

RynnEC: Bringing MLLMs into Embodied World

·
9 authors

Submitted by

gwehr

Virtuous Machines: Towards Artificial General Science

·
7 authors

5

Submitted by

xiaoniqiu

On-Policy RL Meets Off-Policy Experts: Harmonizing Supervised Fine-Tuning and Reinforcement Learning via Dynamic Weighting

·
8 authors

5

Submitted by

anvo25

ViExam: Are Vision Language Models Better than Humans on Vietnamese Multimodal Exam Questions?

·
5 authors

Submitted by

vedantpuri

FLARE: Fast Low-rank Attention Routing Engine

·
6 authors

2

Submitted by

jnanliu

Dissecting Tool-Integrated Reasoning: An Empirical Study and Analysis

·
7 authors

1

Submitted by

ashiq24

Local Scale Equivariance with Latent Deep Equilibrium Canonicalizer

·
7 authors

Submitted by

woutLegiest

Leuvenshtein: Efficient FHE-based Edit Distance Computation with Single Bootstrap per Cell

·
5 authors

Submitted by

Franck-Dernoncourt

mSCoRe: a Multilingual and Scalable Benchmark for Skill-based Commonsense Reasoning

·
3 authors

Submitted by

MrShouxingMa

Refining Contrastive Learning and Homography Relations for Multi-Modal Recommendation

·
4 authors

2