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 7

Submitted by

kefirski

Analyze Feature Flow to Enhance Interpretation and Steering in Language Models

·
4 authors

Submitted by

akhaliq

Gold-medalist Performance in Solving Olympiad Geometry with AlphaGeometry2

·
10 authors

Submitted by

tmeral

ConceptAttention: Diffusion Transformers Learn Highly Interpretable Features

·
5 authors

Submitted by

shash42

Great Models Think Alike and this Undermines AI Oversight

·
9 authors

Submitted by

Hila

DynVFX: Augmenting Real Videos with Dynamic Content

·
4 authors

Submitted by

Zuyan

Ola: Pushing the Frontiers of Omni-Modal Language Model with Progressive Modality Alignment

·
7 authors

Submitted by

akhaliq

Llasa: Scaling Train-Time and Inference-Time Compute for Llama-based Speech Synthesis

·
20 authors

Submitted by

akhaliq

BOLT: Bootstrap Long Chain-of-Thought in Language Models without Distillation

·
6 authors

Submitted by

kkk-an

UltraIF: Advancing Instruction Following from the Wild

·
7 authors

Submitted by

Indulge-Bai

Weak-to-Strong Diffusion with Reflection

·
3 authors

Submitted by

haoxintong

MAGA: MAssive Genre-Audience Reformulation to Pretraining Corpus Expansion

·
3 authors

Submitted by

Lingaaaaaaa

ScoreFlow: Mastering LLM Agent Workflows via Score-based Preference Optimization

·
5 authors

Submitted by

akhaliq

MotionCanvas: Cinematic Shot Design with Controllable Image-to-Video Generation

·
8 authors

Submitted by

ZiyanGuo

MotionLab: Unified Human Motion Generation and Editing via the Motion-Condition-Motion Paradigm

·
4 authors

Submitted by

Jiahang

Beyond Prompt Content: Enhancing LLM Performance via Content-Format Integrated Prompt Optimization

·
9 authors

Submitted by

Yunzhen

PILAF: Optimal Human Preference Sampling for Reward Modeling

·
5 authors

Submitted by

akhaliq

Towards Physical Understanding in Video Generation: A 3D Point Regularization Approach

·
8 authors

Submitted by

Franck-Dernoncourt

ChartCitor: Multi-Agent Framework for Fine-Grained Chart Visual Attribution

·
4 authors

Submitted by

liruiw

Learning Real-World Action-Video Dynamics with Heterogeneous Masked Autoregression

·
4 authors

Submitted by

Franck-Dernoncourt

PlotGen: Multi-Agent LLM-based Scientific Data Visualization via Multimodal Feedback

·
4 authors

Submitted by

Devy1

Enhancing Code Generation for Low-Resource Languages: No Silver Bullet

·
3 authors

Submitted by

YuxinXiao

Speak Easy: Eliciting Harmful Jailbreaks from LLMs with Simple Interactions

·
4 authors