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

Jul 14

Submitted by

wangyuxin87

Test-Time Scaling with Reflective Generative Model

·
11 authors

Submitted by

EricW123456

CLiFT: Compressive Light-Field Tokens for Compute-Efficient and Adaptive Neural Rendering

·
5 authors

Submitted by

llwswyn

Open Vision Reasoner: Transferring Linguistic Cognitive Behavior for Visual Reasoning

·
18 authors

Submitted by

yuntian-deng

NeuralOS: Towards Simulating Operating Systems via Neural Generative Models

·
5 authors

Submitted by

yukimasano

KV Cache Steering for Inducing Reasoning in Small Language Models

·
6 authors

Submitted by

iliashum

Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities

·
3303 authors

Submitted by

kpzhang996

Neural-Driven Image Editing

·
17 authors

Submitted by

JacobYuan

Lumos-1: On Autoregressive Video Generation from a Unified Model Perspective

·
14 authors

Submitted by

yudian

One Token to Fool LLM-as-a-Judge

·
6 authors

Submitted by

dscdyc

From One to More: Contextual Part Latents for 3D Generation

·
13 authors

Submitted by

xwen99

Vision Foundation Models as Effective Visual Tokenizers for Autoregressive Image Generation

·
8 authors

Submitted by

Ksgk-fy

What Has a Foundation Model Found? Using Inductive Bias to Probe for World Models

·
4 authors

Submitted by

Raincleared

BlockFFN: Towards End-Side Acceleration-Friendly Mixture-of-Experts with Chunk-Level Activation Sparsity

·
8 authors

Submitted by

ustc-zhangzm

Robust Multimodal Large Language Models Against Modality Conflict

·
4 authors

Submitted by

maitysubhajit

Doodle Your Keypoints: Sketch-Based Few-Shot Keypoint Detection

·
6 authors

Submitted by

nverma

DOTResize: Reducing LLM Width via Discrete Optimal Transport-based Neuron Merging

·
3 authors

1

Submitted by

Sreyan88

Audio Flamingo 3: Advancing Audio Intelligence with Fully Open Large Audio Language Models

·
11 authors