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 6

Submitted by

amant555

Apriel-1.5-15b-Thinker

ServiceNow-AI

2

Submitted by

AnthonyPeng

Large Reasoning Models Learn Better Alignment from Flawed Thinking

MetaSuperintelligenceLab

3

Submitted by

zichenwen

Efficient Multi-modal Large Language Models via Progressive Consistency Distillation

SJTU

Shanghai Jiao Tong University

Submitted by

SAGE2000

Compose Your Policies! Improving Diffusion-based or Flow-based Robot Policies via Test-time Distribution-level Composition

hkuhk

The University of Hong Kong

Submitted by

zhangchenxu

CoDA: Agentic Systems for Collaborative Data Visualization

google

Submitted by

SpiridonSunRotator

Bridging the Gap Between Promise and Performance for Microscaling FP4 Quantization

ISTA-DASLab

IST Austria Distributed Algorithms and Systems Lab

Submitted by

ShijianDeng

Self-Improvement in Multimodal Large Language Models: A Survey

·
5 authors

Submitted by

jasonrqh

Your Agent May Misevolve: Emergent Risks in Self-evolving LLM Agents

·
11 authors

Submitted by

therem

OrtSAE: Orthogonal Sparse Autoencoders Uncover Atomic Features

·
6 authors

Submitted by

monurcan

Efficient Test-Time Scaling for Small Vision-Language Models

·
3 authors

Submitted by

WeiChihChen

Game-Time: Evaluating Temporal Dynamics in Spoken Language Models

·
10 authors

2

Submitted by

sci-m-wang

REPAIR: Robust Editing via Progressive Adaptive Intervention and Reintegration

ContiAI

Submitted by

taesiri

SurveyBench: How Well Can LLM(-Agents) Write Academic Surveys?

·
9 authors

Submitted by

thomwolf

OpenTSLM: Time-Series Language Models for Reasoning over Multivariate Medical Text- and Time-Series Data

OpenTSLM

OpenTSLM - Open Source Time Series Language Models

Submitted by

seungheondoh

TalkPlay-Tools: Conversational Music Recommendation with LLM Tool Calling

·
3 authors

Submitted by

taesiri

FocusAgent: Simple Yet Effective Ways of Trimming the Large Context of Web Agents

·
10 authors

Submitted by

Norrrrrrr

WAInjectBench: Benchmarking Prompt Injection Detections for Web Agents

·
5 authors

Submitted by

rvandeghen

Triangle Splatting+: Differentiable Rendering with Opaque Triangles

·
9 authors

Submitted by

taesiri

Improving GUI Grounding with Explicit Position-to-Coordinate Mapping

·
7 authors

Submitted by

Vivre

Consolidating Reinforcement Learning for Multimodal Discrete Diffusion Models

·
4 authors

Submitted by

koichisaito

SoundReactor: Frame-level Online Video-to-Audio Generation

Sony

Sony

Submitted by

weizhech

LSPO: Length-aware Dynamic Sampling for Policy Optimization in LLM Reasoning

UniversityofSouthernCalifornia

University of Southern California

Submitted by

hjzheng

Continuously Augmented Discrete Diffusion model for Categorical Generative Modeling

apple

Submitted by

Pamela153

A Practitioner's Guide to Multi-turn Agentic Reinforcement Learning

PEARLS-Lab

Submitted by

stellalisy

Personalized Reasoning: Just-In-Time Personalization and Why LLMs Fail At It

uwnlp

University of Washington NLP

2

Submitted by

jojo23333

Free Lunch Alignment of Text-to-Image Diffusion Models without Preference Image Pairs

UBC-V

University of British Columbia

Submitted by

cmhungsteve

LEAML: Label-Efficient Adaptation to Out-of-Distribution Visual Tasks for Multimodal Large Language Models

·
4 authors

1

Submitted by

taesiri

SpineBench: A Clinically Salient, Level-Aware Benchmark Powered by the SpineMed-450k Corpus

·
26 authors

Submitted by

Madddy

Dale meets Langevin: A Multiplicative Denoising Diffusion Model

IISc

Indian Institute of Science

Submitted by

ethanning

Less LLM, More Documents: Searching for Improved RAG

Carnegie Mellon University School of Computer Science

Submitted by

taesiri

How Confident are Video Models? Empowering Video Models to Express their Uncertainty

·
3 authors

Submitted by

paulcha1025

Align Your Tangent: Training Better Consistency Models via Manifold-Aligned Tangents

·
3 authors

Submitted by

wellbeing

DiffTester: Accelerating Unit Test Generation for Diffusion LLMs via Repetitive Pattern

·
4 authors

2

Submitted by

Yuan-avs

NuRisk: A Visual Question Answering Dataset for Agent-Level Risk Assessment in Autonomous Driving

TUM

Technical University of Munich

1

Submitted by

hpouransari

Pretraining with hierarchical memories: separating long-tail and common knowledge

apple

Submitted by

josephimperial

Scaling Policy Compliance Assessment in Language Models with Policy Reasoning Traces

UOBATH

University Of Bath