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

Dec 16

Submitted by

JinaLeejnl

ReFusion: A Diffusion Large Language Model with Parallel Autoregressive Decoding

·
4 authors

Submitted by

MapleF9

Towards Scalable Pre-training of Visual Tokenizers for Generation

MiniMaxAI

Submitted by

taesiri

Memory in the Age of AI Agents

·
47 authors

Submitted by

Jianxiong

LongVie 2: Multimodal Controllable Ultra-Long Video World Model

·
10 authors

Submitted by

taesiri

QwenLong-L1.5: Post-Training Recipe for Long-Context Reasoning and Memory Management

AlibabaTongyiLab

Submitted by

HaoyuDong

Finch: Benchmarking Finance & Accounting across Spreadsheet-Centric Enterprise Workflows

FinWorkBench

Finch: Finance and Accounting Workflow Benchmark

1

Submitted by

zhangysk

NL2Repo-Bench: Towards Long-Horizon Repository Generation Evaluation of Coding Agents

·
48 authors

Submitted by

soujanyaporia

Error-Free Linear Attention is a Free Lunch: Exact Solution from Continuous-Time Dynamics

declare-lab

Deep Cognition and Language Research (DeCLaRe) Lab

Submitted by

taesiri

KlingAvatar 2.0 Technical Report

KlingTeam

Submitted by

ElsaShaw

MentraSuite: Post-Training Large Language Models for Mental Health Reasoning and Assessment

NextGenWhu

Submitted by

delinqu

Openpi Comet: Competition Solution For 2025 BEHAVIOR Challenge

·
16 authors

Submitted by

zawnpn

Spatial-Aware VLA Pretraining through Visual-Physical Alignment from Human Videos

BeingBeyond

Submitted by

mahirlabibdihan

WebOperator: Action-Aware Tree Search for Autonomous Agents in Web Environment

·
4 authors

Submitted by

zhoutianyi

V-REX: Benchmarking Exploratory Visual Reasoning via Chain-of-Questions

·
6 authors

Submitted by

happinessqq

DrivePI: Spatial-aware 4D MLLM for Unified Autonomous Driving Understanding, Perception, Prediction and Planning

·
9 authors

Submitted by

daehyeonchoi

Toward Ambulatory Vision: Learning Visually-Grounded Active View Selection

KAIST-Visual-AI-Group

KAIST-Visual-AI-Lab

Submitted by

jcenaa

VLSA: Vision-Language-Action Models with Plug-and-Play Safety Constraint Layer

·
6 authors

Submitted by

wangfuyun

Image Diffusion Preview with Consistency Solver

deepmind

Submitted by

ANIYA673

GenieDrive: Towards Physics-Aware Driving World Model with 4D Occupancy Guided Video Generation

·
9 authors

1

Submitted by

weathon

Aesthetic Alignment Risks Assimilation: How Image Generation and Reward Models Reinforce Beauty Bias and Ideological "Censorship"

·
4 authors

1

Submitted by

taesiri

Towards Interactive Intelligence for Digital Humans

·
19 authors

Submitted by

QingyuShi

RecTok: Reconstruction Distillation along Rectified Flow

·
8 authors

Submitted by

Tong98Zhang

CAPTAIN: Semantic Feature Injection for Memorization Mitigation in Text-to-Image Diffusion Models

IVUL-KAUST

Image and Video Understanding Lab

Submitted by

yuanwenyue

LitePT: Lighter Yet Stronger Point Transformer

ethz

Submitted by

kunheekim

Directional Textual Inversion for Personalized Text-to-Image Generation

kaist-ai

Submitted by

taesiri

Video Reality Test: Can AI-Generated ASMR Videos fool VLMs and Humans?

·
9 authors

Submitted by

TariqBerrada

Flowception: Temporally Expansive Flow Matching for Video Generation

Submitted by

zhuomingliu

START: Spatial and Textual Learning for Chart Understanding

amazon-agi

Submitted by

berkegokmen1

Inferring Compositional 4D Scenes without Ever Seeing One

INSAIT-Institute

Institute for Computer Science, Artificial intelligence and Technology

Submitted by

susunghong

DiffusionBrowser: Interactive Diffusion Previews via Multi-Branch Decoders

·
4 authors

Submitted by

Jiasheng1110

Few-Step Distillation for Text-to-Image Generation: A Practical Guide

Alibaba-DAMO-Academy

Submitted by

Mosh

State over Tokens: Characterizing the Role of Reasoning Tokens

·
4 authors

Submitted by

Daniel21Ding

Rethinking Expert Trajectory Utilization in LLM Post-training

·
12 authors

Submitted by

yulu2

FoundationMotion: Auto-Labeling and Reasoning about Spatial Movement in Videos

MIT

Massachusetts Institute of Technology

Submitted by

kjoona

FIN-bench-v2: A Unified and Robust Benchmark Suite for Evaluating Finnish Large Language Models

TurkuNLP

TurkuNLP Research Group

1

Submitted by

Erfan-Nourbakhsh

KD-OCT: Efficient Knowledge Distillation for Clinical-Grade Retinal OCT Classification

·
3 authors

Submitted by

Fanzhri

Learning Robot Manipulation from Audio World Models

·
2 authors

1

Submitted by

mapeAAU

Towards Visual Re-Identification of Fish using Fine-Grained Classification for Electronic Monitoring in Fisheries

dtudk

Technical University of Denmark