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 2

Submitted by

CSJianYang

From Code Foundation Models to Agents and Applications: A Practical Guide to Code Intelligence

Beihang

Beihang University

8

Submitted by

mwxely

LongVT: Incentivizing "Thinking with Long Videos" via Native Tool Calling

lmms-lab

Submitted by

Juanxi

Envision: Benchmarking Unified Understanding & Generation for Causal World Process Insights

opendatalab

Submitted by

Tigerph

Stabilizing Reinforcement Learning with LLMs: Formulation and Practices

Qwen

Qwen

Submitted by

CheeryLJH

How Far Are We from Genuinely Useful Deep Research Agents?

·
18 authors

Submitted by

lmquan

What about gravity in video generation? Post-Training Newton's Laws with Verifiable Rewards

StonyBrook-CVLab

CVLab @ Stony Brook University

Submitted by

Hidir

Infinity-RoPE: Action-Controllable Infinite Video Generation Emerges From Autoregressive Self-Rollout

·
5 authors

Submitted by

ziheng1234

The Consistency Critic: Correcting Inconsistencies in Generated Images via Reference-Guided Attentive Alignment

oyzh1234

Nankai University

Submitted by

taesiri

TUNA: Taming Unified Visual Representations for Native Unified Multimodal Models

4

Submitted by

mlabonne

LFM2 Technical Report

LiquidAI

Submitted by

mbur

Wikontic: Constructing Wikidata-Aligned, Ontology-Aware Knowledge Graphs with Large Language Models

·
4 authors

Submitted by

jnanliu

Rectifying LLM Thought from Lens of Optimization

·
4 authors

Submitted by

GuanjieChen

Flash-DMD: Towards High-Fidelity Few-Step Image Generation with Efficient Distillation and Joint Reinforcement Learning

tencent

Submitted by

yusufma555

GR-RL: Going Dexterous and Precise for Long-Horizon Robotic Manipulation

ByteDance-Seed

Submitted by

Sakits

VLASH: Real-Time VLAs via Future-State-Aware Asynchronous Inference

mit-han-lab

Submitted by

ynhe

InternVideo-Next: Towards General Video Foundation Models without Video-Text Supervision

OpenGVLab

Submitted by

MathsCode

SpeContext: Enabling Efficient Long-context Reasoning with Speculative Context Sparsity in LLMs

SJTU

Shanghai Jiao Tong University

Submitted by

ligongh

Flow Straighter and Faster: Efficient One-Step Generative Modeling via MeanFlow on Rectified Trajectories

·
9 authors

Submitted by

xuyang-liu16

Accelerating Streaming Video Large Language Models via Hierarchical Token Compression

SJUT1

Shanghai JiaoTong University

Submitted by

LucasLoading

Where Culture Fades: Revealing the Cultural Gap in Text-to-Image Generation

·
12 authors

Submitted by

ztwang

PromptBridge: Cross-Model Prompt Transfer for Large Language Models

·
7 authors

Submitted by

YangXiao-nlp

SCALE: Selective Resource Allocation for Overcoming Performance Bottlenecks in Mathematical Test-time Scaling

PolyUHK

The Hong Kong Polytechnic University

Submitted by

yzzyu

Script: Graph-Structured and Query-Conditioned Semantic Token Pruning for Multimodal Large Language Models

HeriotWattUniversity

Heriot-Watt University

2

Submitted by

haodongli

Lotus-2: Advancing Geometric Dense Prediction with Powerful Image Generative Model

·
4 authors

Submitted by

danaleee

StreamGaze: Gaze-Guided Temporal Reasoning and Proactive Understanding in Streaming Videos

adobe-research

Submitted by

shim0114

MultiBanana: A Challenging Benchmark for Multi-Reference Text-to-Image Generation

·
7 authors

Submitted by

chencws

POLARIS: Projection-Orthogonal Least Squares for Robust and Adaptive Inversion in Diffusion Models

·
9 authors

Submitted by

krtanmay147

ORION: Teaching Language Models to Reason Efficiently in the Language of Thought

hippocraticai

Submitted by

ShaoRun

Asking like Socrates: Socrates helps VLMs understand remote sensing images

·
12 authors

Submitted by

hzhouml

Agentic Policy Optimization via Instruction-Policy Co-Evolution

CambUni

University of Cambridge

Submitted by

taesiri

HiconAgent: History Context-aware Policy Optimization for GUI Agents

·
9 authors

Submitted by

royve

Learning Eigenstructures of Unstructured Data Manifolds

Technion

Technion Israel institute of technology

2

Submitted by

aradhye

The Art of Scaling Test-Time Compute for Large Language Models

·
3 authors

Submitted by

taesiri

ChronosObserver: Taming 4D World with Hyperspace Diffusion Sampling

·
5 authors

Submitted by

KrithikV

Generalist Large Language Models Outperform Clinical Tools on Medical Benchmarks

NYU-OLAB

NYU Langone Health OLAB

Submitted by

taesiri

Seeing the Wind from a Falling Leaf

·
8 authors

Submitted by

taesiri

WiseEdit: Benchmarking Cognition- and Creativity-Informed Image Editing

·
9 authors

Submitted by

wyddmw

OpenREAD: Reinforced Open-Ended Reasoing for End-to-End Autonomous Driving with LLM-as-Critic

NanyangTechnologicalUniversity

Nanyang Technological University

Submitted by

sephyli

CauSight: Learning to Supersense for Visual Causal Discovery

2

Submitted by

yj7082126

DreamingComics: A Story Visualization Pipeline via Subject and Layout Customized Generation using Video Models

·
2 authors

Submitted by

acomquest

IndicParam: Benchmark to evaluate LLMs on low-resource Indic Languages

bharatgenai

Submitted by

bwzhi

A Hierarchical Framework for Humanoid Locomotion with Supernumerary Limbs

ImperialCollegeLondon

Imperial College London

Submitted by

yclee

Generative Video Motion Editing with 3D Point Tracks

adobe-research

Submitted by

zuazo

MEGConformer: Conformer-Based MEG Decoder for Robust Speech and Phoneme Classification

HiTZ

Submitted by

MElHuseyni

Doppler-Enhanced Deep Learning: Improving Thyroid Nodule Segmentation with YOLOv5 Instance Segmentation

·
1 authors

2

Submitted by

skoneru

OmniFusion: Simultaneous Multilingual Multimodal Translations via Modular Fusion

kit-isl-ai4lt

ISL & AI4LT @ KIT

Submitted by

pritamdeka

Structured Extraction from Business Process Diagrams Using Vision-Language Models

·
2 authors