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

Mar 20

Submitted by

xufangzhi

φ-Decoding: Adaptive Foresight Sampling for Balanced Inference-Time Exploration and Exploitation

·
7 authors

1

Submitted by

zzzrw

DeepMesh: Auto-Regressive Artist-mesh Creation with Reinforcement Learning

·
7 authors

2

Submitted by

davidchan

TULIP: Towards Unified Language-Image Pretraining

·
9 authors

1

Submitted by

j4kn

Cube: A Roblox View of 3D Intelligence

·
45 authors

1

Submitted by

akhaliq

Temporal Regularization Makes Your Video Generator Stronger

·
8 authors

Submitted by

Agorium

Efficient Personalization of Quantized Diffusion Model without Backpropagation

·
4 authors

1

Submitted by

jing-bi

VERIFY: A Benchmark of Visual Explanation and Reasoning for Investigating Multimodal Reasoning Fidelity

·
11 authors

1

Submitted by

QizhiPei

MetaLadder: Ascending Mathematical Solution Quality via Analogical-Problem Reasoning Transfer

·
8 authors

Submitted by

ylu610

Optimizing Decomposition for Optimal Claim Verification

·
4 authors

Submitted by

julianjuaner

STEVE: AStep Verification Pipeline for Computer-use Agent Training

·
6 authors

Submitted by

zichenwen

LEGION: Learning to Ground and Explain for Synthetic Image Detection

·
11 authors

1

Submitted by

susunghong

MusicInfuser: Making Video Diffusion Listen and Dance

·
4 authors

1

Submitted by

StarJiaxing

ViSpeak: Visual Instruction Feedback in Streaming Videos

·
9 authors

Submitted by

VentureZJ

GKG-LLM: A Unified Framework for Generalized Knowledge Graph Construction

·
6 authors

1

Submitted by

Allen8

Mitigating Visual Forgetting via Take-along Visual Conditioning for Multi-modal Long CoT Reasoning

·
4 authors

1

Submitted by

ChaolongYang

Unlock Pose Diversity: Accurate and Efficient Implicit Keypoint-based Spatiotemporal Diffusion for Audio-driven Talking Portrait

·
10 authors

1

Submitted by

akhaliq

Decompositional Neural Scene Reconstruction with Generative Diffusion Prior

·
7 authors

Submitted by

parshinsh

LLM-FE: Automated Feature Engineering for Tabular Data with LLMs as Evolutionary Optimizers

·
3 authors

1

Submitted by

SivilTaram

SkyLadder: Better and Faster Pretraining via Context Window Scheduling

·
7 authors

Submitted by

lavriz

ELTEX: A Framework for Domain-Driven Synthetic Data Generation

·
5 authors

1

Submitted by

vsubhashini

CURIE: Evaluating LLMs On Multitask Scientific Long Context Understanding and Reasoning

·
31 authors

1

Submitted by

yifeizhou

SWEET-RL: Training Multi-Turn LLM Agents on Collaborative Reasoning Tasks

·
7 authors