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 19

Submitted by

Yoohao

Soundwave: Less is More for Speech-Text Alignment in LLMs

·
6 authors

Submitted by

mbur

Cramming 1568 Tokens into a Single Vector and Back Again: Exploring the Limits of Embedding Space Capacity

·
4 authors

Submitted by

harryjo97

Continuous Diffusion Model for Language Modeling

·
2 authors

Submitted by

liulj13

Phantom: Subject-consistent video generation via cross-modal alignment

·
7 authors

Submitted by

akhaliq

Magma: A Foundation Model for Multimodal AI Agents

·
13 authors

Submitted by

LegendBC

Multimodal Mamba: Decoder-only Multimodal State Space Model via Quadratic to Linear Distillation

·
8 authors

Submitted by

Ray2333

Rethinking Diverse Human Preference Learning through Principal Component Analysis

·
8 authors

Submitted by

jiminHuang

FLAG-Trader: Fusion LLM-Agent with Gradient-based Reinforcement Learning for Financial Trading

·
13 authors

Submitted by

yaraksen

You Do Not Fully Utilize Transformer's Representation Capacity

·
5 authors

Submitted by

qizekun

SoFar: Language-Grounded Orientation Bridges Spatial Reasoning and Object Manipulation

·
18 authors

Submitted by

Seanie-lee

SafeRoute: Adaptive Model Selection for Efficient and Accurate Safety Guardrails in Large Language Models

·
8 authors

Submitted by

Kaichengalex

RealSyn: An Effective and Scalable Multimodal Interleaved Document Transformation Paradigm

·
9 authors

Submitted by

MengkangHu

Text2World: Benchmarking Large Language Models for Symbolic World Model Generation

·
9 authors

Submitted by

lupantech

OctoTools: An Agentic Framework with Extensible Tools for Complex Reasoning

·
6 authors

Submitted by

akhaliq

Revisiting the Test-Time Scaling of o1-like Models: Do they Truly Possess Test-Time Scaling Capabilities?

·
5 authors

Submitted by

kittttttt

PAFT: Prompt-Agnostic Fine-Tuning

·
5 authors

Submitted by

xiaoda99

MUDDFormer: Breaking Residual Bottlenecks in Transformers via Multiway Dynamic Dense Connections

·
4 authors

Submitted by

leavendough

Atom of Thoughts for Markov LLM Test-Time Scaling

·
6 authors

Submitted by

wannature

HealthGPT: A Medical Large Vision-Language Model for Unifying Comprehension and Generation via Heterogeneous Knowledge Adaptation

·
15 authors

Submitted by

wdlctc

HeadInfer: Memory-Efficient LLM Inference by Head-wise Offloading

·
10 authors

Submitted by

nielsr

YOLOv12: Attention-Centric Real-Time Object Detectors

·
3 authors

Submitted by

ArthurDouillard

Eager Updates For Overlapped Communication and Computation in DiLoCo

·
3 authors

Submitted by

lnair

Flow-of-Options: Diversified and Improved LLM Reasoning by Thinking Through Options

·
3 authors

Submitted by

xw-eric

The Hidden Risks of Large Reasoning Models: A Safety Assessment of R1

·
8 authors

Submitted by

DonJoey

Crowd Comparative Reasoning: Unlocking Comprehensive Evaluations for LLM-as-a-Judge

·
11 authors

Submitted by

Ziruibest

Injecting Domain-Specific Knowledge into Large Language Models: A Comprehensive Survey

·
7 authors

Submitted by

roeiherz

Pre-training Auto-regressive Robotic Models with 4D Representations

·
8 authors

Submitted by

yixuantt

FinMTEB: Finance Massive Text Embedding Benchmark

·
2 authors

Submitted by

nijingchao

Harnessing Vision Models for Time Series Analysis: A Survey

·
8 authors

Submitted by

Dominic789654

Perovskite-LLM: Knowledge-Enhanced Large Language Models for Perovskite Solar Cell Research

·
10 authors

Submitted by

Geralt-Targaryen

Multilingual Encoder Knows more than You Realize: Shared Weights Pretraining for Extremely Low-Resource Languages

·
7 authors

Submitted by

ThreeSR

Scaling Autonomous Agents via Automatic Reward Modeling And Planning

·
5 authors