new

Get trending papers in your email inbox once a day!

Get trending papers in your email inbox!

Daily Papers

by AK and the research community

Feb 10

Submitted by

myownskyW7

VideoRoPE: What Makes for Good Video Rotary Position Embedding?

·
12 authors

Submitted by

akhaliq

Goku: Flow Based Video Generative Foundation Models

·
22 authors

Submitted by

PY007

Fast Video Generation with Sliding Tile Attention

·
7 authors

Submitted by

akhaliq

Scaling up Test-Time Compute with Latent Reasoning: A Recurrent Depth Approach

·
9 authors

Submitted by

d-alistarh

QuEST: Stable Training of LLMs with 1-Bit Weights and Activations

·
6 authors

Submitted by

yulunliu

AuraFusion360: Augmented Unseen Region Alignment for Reference-based 360° Unbounded Scene Inpainting

·
11 authors

Submitted by

ydeng9

DuoGuard: A Two-Player RL-Driven Framework for Multilingual LLM Guardrails

·
5 authors

Submitted by

akhaliq

FlashVideo:Flowing Fidelity to Detail for Efficient High-Resolution Video Generation

·
10 authors

Submitted by

akhaliq

Agency Is Frame-Dependent

·
16 authors

Submitted by

akhaliq

Generating Symbolic World Models via Test-time Scaling of Large Language Models

·
8 authors

Submitted by

akhaliq

Step Back to Leap Forward: Self-Backtracking for Boosting Reasoning of Language Models

·
8 authors

Submitted by

Eleven-P

CMoE: Fast Carving of Mixture-of-Experts for Efficient LLM Inference

·
8 authors

Submitted by

danielm1405

No Task Left Behind: Isotropic Model Merging with Common and Task-Specific Subspaces

·
6 authors

Submitted by

akhaliq

On-device Sora: Enabling Diffusion-Based Text-to-Video Generation for Mobile Devices

·
6 authors

Submitted by

akhaliq

Linear Correlation in LM's Compositional Generalization and Hallucination

·
5 authors

Submitted by

nielsr

Scaling Laws in Patchification: An Image Is Worth 50,176 Tokens And More

·
7 authors

Submitted by

zhaoyue-zephyrus

QLIP: Text-Aligned Visual Tokenization Unifies Auto-Regressive Multimodal Understanding and Generation

·
9 authors

Submitted by

akhaliq

CodeSteer: Symbolic-Augmented Language Models via Code/Text Guidance

·
5 authors

Submitted by

rohitsaxena

Lost in Time: Clock and Calendar Understanding Challenges in Multimodal LLMs

·
3 authors

Submitted by

orybkin

Value-Based Deep RL Scales Predictably

·
7 authors

Submitted by

yuweiyin

ARR: Question Answering with Large Language Models via Analyzing, Retrieving, and Reasoning

·
2 authors

Submitted by

amanchadha

YINYANG-ALIGN: Benchmarking Contradictory Objectives and Proposing Multi-Objective Optimization based DPO for Text-to-Image Alignment

·
8 authors

Submitted by

AlexCuadron

Adaptive Semantic Prompt Caching with VectorQ

·
8 authors

Submitted by

XiaotingQin

MEETING DELEGATE: Benchmarking LLMs on Attending Meetings on Our Behalf

·
8 authors

Submitted by

sinatayebati

SPARC: Subspace-Aware Prompt Adaptation for Robust Continual Learning in LLMs

·
5 authors

Submitted by

nielsr

Continuous 3D Perception Model with Persistent State

·
5 authors

Submitted by

sinatayebati

Intelligent Sensing-to-Action for Robust Autonomy at the Edge: Opportunities and Challenges

·
12 authors