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

Oct 7

Submitted by

KevinQHLin

Paper2Video: Automatic Video Generation from Scientific Papers

showlab

Submitted by

YuchengShi

MITS: Enhanced Tree Search Reasoning for LLMs via Pointwise Mutual Information

UGA-AI

University of Georgia

2

Submitted by

taesiri

Video-LMM Post-Training: A Deep Dive into Video Reasoning with Large Multimodal Models

·
27 authors

Submitted by

taesiri

VChain: Chain-of-Visual-Thought for Reasoning in Video Generation

·
6 authors

Submitted by

taesiri

Agentic Context Engineering: Evolving Contexts for Self-Improving Language Models

·
13 authors

Submitted by

P2333

Imperceptible Jailbreaking against Large Language Models

sail

Submitted by

raymin0223

Hybrid Architectures for Language Models: Systematic Analysis and Design Insights

MetaSuperintelligenceLab

2

Submitted by

ofivite

Optimal Scaling Needs Optimal Norm

·
4 authors

Submitted by

AdamF92

Reactive Transformer (RxT) -- Stateful Real-Time Processing for Event-Driven Reactive Language Models

ReactiveAI

Submitted by

shrimai19

Front-Loading Reasoning: The Synergy between Pretraining and Post-Training Data

nvidia

3

Submitted by

XingweiT

Fine-Tuning on Noisy Instructions: Effects on Generalization and Performance

·
3 authors

2

Submitted by

JackyZhuo

Factuality Matters: When Image Generation and Editing Meet Structured Visuals

·
11 authors

Submitted by

zhhli

Judging with Confidence: Calibrating Autoraters to Preference Distributions

google

2

Submitted by

haizhongzheng

Prosperity before Collapse: How Far Can Off-Policy RL Reach with Stale Data on LLMs?

Carnegie Mellon University

Submitted by

weqweasdas

Reinforce-Ada: An Adaptive Sampling Framework for Reinforce-Style LLM Training

RLHFlow

Submitted by

Cqy2019

MOSS-Speech: Towards True Speech-to-Speech Models Without Text Guidance

fnlp

OpenMOSS (SII, Fudan NLP)

Submitted by

taesiri

SwiReasoning: Switch-Thinking in Latent and Explicit for Pareto-Superior Reasoning LLMs

microsoft

Submitted by

mujianijan

Self-Reflective Generation at Test Time

·
8 authors

Submitted by

jayw

ChronoEdit: Towards Temporal Reasoning for Image Editing and World Simulation

nvidia

Submitted by

RohamKoohestani

Code4MeV2: a Research-oriented Code-completion Platform

AISE research lab at TU Delft

Submitted by

taesiri

Watch and Learn: Learning to Use Computers from Online Videos

google

Submitted by

danielhzlin

EvolProver: Advancing Automated Theorem Proving by Evolving Formalized Problems via Symmetry and Difficulty

·
9 authors

2

Submitted by

qcz

Good Intentions Beyond ACL: Who Does NLP for Social Good, and Where?

·
6 authors

Submitted by

hisoka94

MoME: Mixture of Matryoshka Experts for Audio-Visual Speech Recognition

ImperialCollegeLondon

Imperial College London

2

Submitted by

saksornr

Thai Semantic End-of-Turn Detection for Real-Time Voice Agents

·
4 authors

2

Submitted by

epark

Optimized Minimal 4D Gaussian Splatting

·
10 authors

Submitted by

skyil7

HiKE: Hierarchical Evaluation Framework for Korean-English Code-Switching Speech Recognition

thetaone-ai

Submitted by

Luffuly

Character Mixing for Video Generation

MBZUAI

Mohamed Bin Zayed University of Artificial Intelligence

Submitted by

garibida

SAEdit: Token-level control for continuous image editing via Sparse AutoEncoder

·
6 authors

2

Submitted by

Lillianwei

Alignment Tipping Process: How Self-Evolution Pushes LLM Agents Off the Rails

·
10 authors

Submitted by

lucasbandarkar

Multilingual Routing in Mixture-of-Experts

UCLA

University of California, Los Angeles

Submitted by

wzywp

Slow-Fast Policy Optimization: Reposition-Before-Update for LLM Reasoning

·
8 authors

Submitted by

pihull

LLMSQL: Upgrading WikiSQL for the LLM Era of Text-to-SQL

llmsql-bench

Submitted by

amrit0714

Test-Time Scaling in Diffusion LLMs via Hidden Semi-Autoregressive Experts

University of Central Florida

2

Submitted by

jonhue

Learning on the Job: Test-Time Curricula for Targeted Reinforcement Learning

lasgroup

LAS @ ETH Zurich

Submitted by

charleslwang

Utility-Learning Tension in Self-Modifying Agents

·
3 authors

2

Submitted by

dwright37

Epistemic Diversity and Knowledge Collapse in Large Language Models

copenlu

2

Submitted by

eliebak

Paris: A Decentralized Trained Open-Weight Diffusion Model

·
4 authors

Submitted by

niloofarm

Position: Privacy Is Not Just Memorization!

cmu-lti

Submitted by

zhenyupan

AdvEvo-MARL: Shaping Internalized Safety through Adversarial Co-Evolution in Multi-Agent Reinforcement Learning

·
16 authors

Submitted by

yurun-chen

Graph2Eval: Automatic Multimodal Task Generation for Agents via Knowledge Graphs

·
11 authors

Submitted by

xuefeng-xu

Power Transform Revisited: Numerically Stable, and Federated

·
2 authors

Submitted by

xuefeng-xu

Federated Computation of ROC and PR Curves

·
2 authors

Submitted by

jacobkahn

CWM: An Open-Weights LLM for Research on Code Generation with World Models