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 4

Submitted by

akhaliq

OmniHuman-1: Rethinking the Scaling-Up of One-Stage Conditioned Human Animation Models

·
5 authors

Submitted by

Myashka

The Differences Between Direct Alignment Algorithms are a Blur

·
5 authors

Submitted by

hanbin

Process Reinforcement through Implicit Rewards

·
23 authors

Submitted by

wjldw

Preference Leakage: A Contamination Problem in LLM-as-a-judge

·
9 authors

Submitted by

ahmed-masry

AlignVLM: Bridging Vision and Language Latent Spaces for Multimodal Understanding

·
22 authors

Submitted by

jimi888

SafeRAG: Benchmarking Security in Retrieval-Augmented Generation of Large Language Model

·
11 authors

Submitted by

RohitGandikota

SliderSpace: Decomposing the Visual Capabilities of Diffusion Models

·
6 authors

Submitted by

huanqia

MM-IQ: Benchmarking Human-Like Abstraction and Reasoning in Multimodal Models

·
3 authors

Submitted by

yiren98

MakeAnything: Harnessing Diffusion Transformers for Multi-Domain Procedural Sequence Generation

·
3 authors

Submitted by

xinyan233333

DeepRAG: Thinking to Retrieval Step by Step for Large Language Models

·
9 authors

Submitted by

akhaliq

Scaling Embedding Layers in Language Models

·
8 authors

Submitted by

ahmedheakl

AIN: The Arabic INclusive Large Multimodal Model

·
7 authors

Submitted by

dongwonjo

FastKV: KV Cache Compression for Fast Long-Context Processing with Token-Selective Propagation

·
4 authors

Submitted by

akhaliq

ZebraLogic: On the Scaling Limits of LLMs for Logical Reasoning

·
7 authors

Submitted by

PAlbert31

RandLoRA: Full-rank parameter-efficient fine-tuning of large models

·
6 authors

Submitted by

akhaliq

The Jumping Reasoning Curve? Tracking the Evolution of Reasoning Performance in GPT-[n] and o-[n] Models on Multimodal Puzzles

·
4 authors

Submitted by

hba123

Almost Surely Safe Alignment of Large Language Models at Inference-Time

·
6 authors

Submitted by

akhaliq

Improving Transformer World Models for Data-Efficient RL

·
8 authors

Submitted by

arjunguha

PhD Knowledge Not Required: A Reasoning Challenge for Large Language Models

·
8 authors

Submitted by

quandao10

Improved Training Technique for Latent Consistency Models

·
5 authors

Submitted by

archiki

Learning to Generate Unit Tests for Automated Debugging

·
5 authors

Submitted by

akshat57

Lifelong Sequential Knowledge Editing without Model Degradation

·
6 authors

Submitted by

Bowen232

LongDPO: Unlock Better Long-form Generation Abilities for LLMs via Critique-augmented Stepwise Information

·
6 authors

Submitted by

moein99

A Study on the Performance of U-Net Modifications in Retroperitoneal Tumor Segmentation

·
8 authors

Submitted by

vshrivas

Language Models Prefer What They Know: Relative Confidence Estimation via Confidence Preferences

·
3 authors

Submitted by

EdwinDdeJong

Current Pathology Foundation Models are unrobust to Medical Center Differences

·
3 authors