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

Apr 9

Submitted by

CH3COOK

OmniSVG: A Unified Scalable Vector Graphics Generation Model

·
9 authors

Submitted by

d-alistarh

Hogwild! Inference: Parallel LLM Generation via Concurrent Attention

·
8 authors

Submitted by

xuchensong

Skywork R1V: Pioneering Multimodal Reasoning with Chain-of-Thought

·
15 authors

Submitted by

BryanW

An Empirical Study of GPT-4o Image Generation Capabilities

·
19 authors

2

Submitted by

SiweiWu

COIG-P: A High-Quality and Large-Scale Chinese Preference Dataset for Alignment with Human Values

·
32 authors

2

Submitted by

fenfan

Less-to-More Generalization: Unlocking More Controllability by In-Context Generation

·
6 authors

Submitted by

kevinzhong

HybriMoE: Hybrid CPU-GPU Scheduling and Cache Management for Efficient MoE Inference

·
6 authors

Submitted by

myownskyW7

HiFlow: Training-free High-Resolution Image Generation with Flow-Aligned Guidance

·
10 authors

3

Submitted by

pkuHaowei

Generative Evaluation of Complex Reasoning in Large Language Models

·
10 authors

Submitted by

Awiny

V-MAGE: A Game Evaluation Framework for Assessing Visual-Centric Capabilities in Multimodal Large Language Models

·
8 authors

Submitted by

Orannue

Tuning-Free Image Editing with Fidelity and Editability via Unified Latent Diffusion Model

·
5 authors

Submitted by

yuyijiong

Accelerate Parallelizable Reasoning via Parallel Decoding within One Sequence

·
1 authors

2

Submitted by

boyuanzheng010

SkillWeaver: Web Agents can Self-Improve by Discovering and Honing Skills

·
11 authors

Submitted by

MaksimSTW

Efficient Reinforcement Finetuning via Adaptive Curriculum Learning

·
5 authors

Submitted by

teapot123

CrossWordBench: Evaluating the Reasoning Capabilities of LLMs and LVLMs with Controllable Puzzle Generation

·
7 authors

Submitted by

akhaliq

Leanabell-Prover: Posttraining Scaling in Formal Reasoning

·
9 authors

Submitted by

zchuning

Unified World Models: Coupling Video and Action Diffusion for Pretraining on Large Robotic Datasets

·
6 authors

Submitted by

msj9817

ProtoGCD: Unified and Unbiased Prototype Learning for Generalized Category Discovery

·
4 authors