🤗 Hugging Face - codenm.no2 · Scour

ELT: Elastic Looped Transformers for Visual Generation 🧠LLM

arxiv.org·2d

Tencent-Hunyuan/HY-Embodied: A Family of Embodied Foundation Models for Real-World Agents (Tencent Robotics X × HY Vision Team) 🎭Anthropic Claude

github.com·2d

Recursive Language Models (RLMs): The Answer to Context Rot in Large Language Models 🧠LLM

pub.towardsai.net

·2d

EPIR: An Efficient Patch Tokenization, Integration and Representation Framework for Micro-expression Recognition 👁️Multimodal AI

arxiv.org·5d

EventFace: Event-Based Face Recognition via Structure-Driven Spatiotemporal Modeling 👁️Multimodal AI

arxiv.org·6d

Relational Preference Encoding in Looped Transformer Internal States 🤖Large Language Models

arxiv.org·1d

ETCH-X: Robustify Expressive Body Fitting to Clothed Humans with Composable Datasets 🎭Anthropic Claude

arxiv.org·5d

Revisiting Anisotropy in Language Transformers: The Geometry of Learning Dynamics 🧠LLM

arxiv.org·2d

Bootstrapping Sign Language Annotations with Sign Language Models 👁️Multimodal AI

arxiv.org·5d

UDAPose: Unsupervised Domain Adaptation for Low-Light Human Pose Estimation 👁️Multimodal AI

arxiv.org·1d

Cross-Lingual Attention Distillation with Personality-Informed Generative Augmentation for Multilingual Personality Recognition 🧠LLM

arxiv.org·2d

Tarot-SAM3: Training-free SAM3 for Any Referring Expression Segmentation 🧠LLM

arxiv.org·5d

MM-LIMA: Less Is More for Alignment in Multi-Modal Datasets 👁️Multimodal AI

arxiv.org·1d

Layerwise Dynamics for In-Context Classification in Transformers 🧠LLM

arxiv.org·1d

A-MBER: Affective Memory Benchmark for Emotion Recognition 👁️Multimodal AI

arxiv.org·6d

BlendFusion -- Scalable Synthetic Data Generation for Diffusion Model Training 🎨Generative AI

arxiv.org·2d

Loop, Think, & Generalize: Implicit Reasoning in Recurrent-Depth Transformers 💬LLMs

arxiv.org·5d

VisionFoundry: Teaching VLMs Visual Perception with Synthetic Images 🎨Generative AI

arxiv.org·2d

EquiformerV3: Scaling Efficient, Expressive, and General SE(3)-Equivariant Graph Attention Transformers 🧠LLM

arxiv.org·2d

Multiple Domain Generalization Using Category Information Independent of Domain Differences 👁️Multimodal AI

arxiv.org·6d

Loading more...