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

Nov 11

Submitted by

SempraETY

Few-Step Streaming Video Generation via Condition Shifting

Tsinghua University

Submitted by

ammarali32

Tree-Ising: Repairing Language Models with Bit-Level Ising Edits

·
2 authors

Submitted by

dkliang

World In-Context Learning for Agentic Robot Manipulation

ArcheOne-AI

Submitted by

YuminChoi

Don't Just Trust Your Memory: Evidence-Linked Memory Reduces Memory-Induced Degradation in LLM Agents

kaist-ai

Submitted by

XiaotongLi97

dNaViT: Discrete Codes are General-Purpose Visual Representations

meituan-longcat

Submitted by

erisura

One Table, Many Queries: Benchmarking Generalist Tabular Models Across Generation, Imputation, and Prediction

stable-ai

Submitted by

shenjunhao

MMDM: Measuring Massive Multitask Decision Making

CUHKDBGROUP

The Chinese University of Hong Kong

Submitted by

JamesK2W

Embodied First Exam

MLL-Lab

Submitted by

ChenZhongxi

DexForesight: Grounding Dexterous Policies with Implicit Spatial Foresight

Sharpa-Robotics

Submitted by

YupengCao

FINCOSMOS: An Open-World Evaluation Paradigm for Agents in Finance

TheFinAI

4

Submitted by

pbicho

MACaQ: Fast, Model Agnostic Calibrated Quantization for Low-Precision Weights and Activations

huawei-csl

HUAWEI Computing Systems Lab

Submitted by

LeeSangHoon

WaveGen: Truly End-to-End Waveform Generation via Internal Spectral Trajectory Learning

Ajou

Ajou university

Submitted by

galaxy-1

DepthGraft: Structural Regularization through Hierarchical Cross-Layer KV Reconstruction

dots-studio

Submitted by

yikuuun

ProTEUS: A mutation-resolved world model for closed-loop protein evolution

·
8 authors

Submitted by

Jacklu0831

The Surprising Effectiveness of Deleting Weights in LLM Post-Training

agentic-learning-ai-lab

agentic learning ai lab

Submitted by

kittyhy

PhyRubric: Rubric-Grounded Diagnostic Evaluation of Physical Commonsense in Text-to-Video Generation

·
8 authors

Submitted by

INTOSYN-AI

From Tool State to Scientific Action: Auditing Decision Provenance in Biomedical Research Agents

INTOSYN-AI-Labs

INTOSYN AI Labs

3

Submitted by

bowen-zuo

Test-Time Scaling for Diffusion Language Models with Frequency-Aware Remasking

ucriverside

Submitted by

Harold328

PhysOPSD: Code as Privilege for Physically Plausible Video Generation

AlibabaTongyiLab

Submitted by

torpedo2003

Micius-Flash: Lightweight Agentic Intelligence for Engineering

zhiman-ai

3

Submitted by

benni23

Is Your Robot's Memory Just a Clock? Temporal Shortcuts in Memory-Augmented VLA Policies

NanyangTechnologicalUniversity

Nanyang Technological University

Submitted by

omtekyav

Are Causal Neuron Circuits Unique and Transferable?

·
1 authors

Submitted by

zhuqinfeng

LEASH: Stay Safe in Agentic Robotics

UoLiverpool

University of Liverpool

Submitted by

Greenbean

Market-Conditioned JEPA: Learning from Unpredictable Market Shocks

OpenFinMind

Submitted by

Xkev

Blind Variation, Selective Retention: Improving Creative Idea Generation in AI Scientists

StanfordUniversity

Stanford University

Submitted by

haoranranranran

EarthRecord: From Pixels to Land Change with Multimodal Agents over Four Decades of Satellite Imagery

AIEyesTech

AIEyes Technologies (Hong Kong) Co., Limited

Submitted by

Frinkleko

Shortcuts and Boundaries: Verifiable RL Misalignment and Contextual Safety Learning

EverywhereSafety

Everywhere Safety

Submitted by

optimusPrimeBee

Are Dense Rewards Worth Their Tokens in GRPO?

Case Western Reserve University

7

Submitted by

FrankLuox

ExRL: Sample-Efficient Online Adaptation of Long-Chunk Policies via Execution Length Control

·
8 authors

Submitted by

jefftan969

DyCraft: An Agentic System for Long-Horizon 4D Scene Generation

StanfordUniversity

Stanford University

Submitted by

alexshtf

TorchCurves: Differentiable Parametric Curves

·
1 authors

Submitted by

MaplesWCT

EVAThink: Evidence Sufficiency-Guided Training for Adaptive Thinking in Video Understanding

·
5 authors

Submitted by

nuskonghou

Learning to Act with World Models by Valuing What Comes Next

NationalUniversityofSingapore

National University of Singapore

Submitted by

sachithabey

Predictive Surprise as Self-Grounding Concept Bottleneck for Interpretable Time Series

NanyangTechnologicalUniversity

Nanyang Technological University

Submitted by

MrPatoVera

Visual Similarity in Adult Word Extension and Artificial Word Learning

·
1 authors

2

Submitted by

PhySwing

Sable: A Small-Field Sumcheck Argument for Bit-Exact Inference of Large Language Models

MoonMath-ai

Submitted by

shotegni

Lipschitz-Controlled Flow Matching for Robust Image Restoration

paderborn-university

Universität Paderborn

Submitted by

JimmyLiaoo

LO-World: Unified BEV Latent Modeling for Joint 4D Occupancy and LiDAR Forecasting

·
4 authors

Submitted by

moein99

Prompt2Echo (P2Echo): Text-Prompted Multi-View Echocardiography Segmentation with One Model

UBC-V

University of British Columbia