Adina Yakefu

Paper • 2406.15718 • Published 5 days ago • 11 •

New activity in tsinghua-ee/SALMONN-7B-gradio 1 day ago

Add paper link to link the demo to the paper on Daily Papers page

#3 opened 1 day ago by

AdinaY

New activity in tsinghua-ee/SALMONN 1 day ago

Add paper link

#2 opened 1 day ago by

AdinaY

commented 2 papers 1 day ago

Beyond the Turn-Based Game: Enabling Real-Time Conversations with Duplex Models

Paper • 2406.16772 • Published 2 days ago • 3 •

OlympicArena Medal Ranks: Who Is the Most Intelligent AI So Far?

Paper • 2406.16714 • Published 2 days ago • 8 •

New activity in GAIR/OlympicArena 1 day ago

Add paper link

#2 opened 1 day ago by

AdinaY

commented 3 papers 1 day ago

AutoDetect: Towards a Unified Framework for Automated Weakness Detection in Large Language Models

Paper • 2406.16860 • Published 2 days ago • 31 •

Cambrian-1: A Fully Open, Vision-Centric Exploration of Multimodal LLMs

Paper • 2406.15877 • Published 4 days ago • 35 •

BigCodeBench: Benchmarking Code Generation with Diverse Function Calls and Complex Instructions

8

New activity in bigcode/bigcodebench-leaderboard 1 day ago

Add paper link to link the leaderboard to the paper on Daily Papers. page.

#4 opened 1 day ago by

AdinaY

New activity in bigai-nlco/VideoHallucer 1 day ago

Add paper link

#1 opened 1 day ago by

AdinaY

commented 3 papers 2 days ago

Evaluating RAG-Fusion with RAGElo: an Automated Elo-based Framework

Paper • 2406.14783 • Published 6 days ago • 12 •

Paper • 2406.13457 • Published 7 days ago • 12 •

EvTexture: Event-driven Texture Enhancement for Video Super-Resolution

Paper • 2406.14599 • Published 6 days ago • 14 •

Stylebreeder: Exploring and Democratizing Artistic Styles through Text-to-Image Models

New activity in TIGER-Lab/LongRAG 2 days ago

Add paper link

Paper • 2406.14319 • Published 6 days ago • 13 •

#1 opened 2 days ago by

AdinaY

commented 2 papers 5 days ago

LiveMind: Low-latency Large Language Models with Simultaneous Inference

Paper • 2406.14347 • Published 6 days ago • 93 •

$\nabla^2$DFT: A Universal Quantum Chemistry Dataset of Drug-Like Molecules and a Benchmark for Neural Network Potentials

New activity in opencompass/open_vlm_leaderboard 5 days ago

Add paper link

Paper • 2406.12034 • Published 9 days ago • 12 •

#10 opened 5 days ago by

AdinaY

commented 3 papers 6 days ago

Self-MoE: Towards Compositional Large Language Models with Self-Specialized Experts

Paper • 2406.11801 • Published 9 days ago • 15 •

Safety Arithmetic: A Framework for Test-time Safety Alignment of Language Models by Steering Parameters and Activations

Paper • 2406.12849 • Published 8 days ago • 45 •

Depth Anywhere: Enhancing 360 Monocular Depth Estimation via Perspective Distillation and Unlabeled Data Augmentation

New activity in Albert-NHWang/Depth-Anywhere-App 6 days ago

add paper link to connect the demo with its paper on Daily Papers page

Paper • 2406.11431 • Published 9 days ago • 4 •

#1 opened 6 days ago by

AdinaY

commented a paper 6 days ago

Super(ficial)-alignment: Strong Models May Deceive Weak Models in Weak-to-Strong Generalization

New activity in Wenetspeech4TTS/Audiodec-Valle-Wenetspeech4TTS 6 days ago

Add model card

Paper • 2406.12753 • Published 8 days ago • 14 •

#1 opened 8 days ago by

AdinaY

commented a paper 7 days ago

OlympicArena: Benchmarking Multi-discipline Cognitive Reasoning for Superintelligent AI

Paper • 2406.10163 • Published 12 days ago • 23 •

New activity in GAIR/OlympicArenaSubmission 7 days ago

Add paper link to connect the Space to its paper on Daily Papers page

#1 opened 7 days ago by

AdinaY

commented a paper 7 days ago

MeshAnything: Artist-Created Mesh Generation with Autoregressive Transformers

Paper • 2406.12793 • Published 8 days ago • 26 •

New activity in VLLMs/MIRB 7 days ago

Add paper link to connect the dataset to its paper on Daily Papers page

#2 opened 7 days ago by

AdinaY

commented 2 papers 7 days ago

ChatGLM: A Family of Large Language Models from GLM-130B to GLM-4 All Tools

Paper • 2406.12275 • Published 8 days ago • 28 •

VoCo-LLaMA: Towards Vision Compression with Large Language Models

10

New activity in deepseek-ai/DeepSeek-Coder-V2-Base 7 days ago

Add paper link

#2 opened 7 days ago by

AdinaY

commented a paper 8 days ago

Exploring the Role of Large Language Models in Prompt Encoding for Diffusion Models

Paper • 2406.11831 • Published 9 days ago • 17 •

Paper • 2406.10111 • Published 12 days ago • 6 •

commented a paper 9 days ago

GaussianSR: 3D Gaussian Super-Resolution with 2D Diffusion Priors

Paper • 2406.08673 • Published 14 days ago • 14 •

commented 2 papers 12 days ago

HelpSteer2: Open-source dataset for training top-performing reward models

Paper • 2406.08587 • Published 14 days ago • 14 •

CS-Bench: A Comprehensive Benchmark for Large Language Models towards Computer Science Mastery

Paper • 2406.09162 • Published 13 days ago • 13 •

New activity in CS-Bench/CS-Bench 12 days ago

Add paper link to connect dataset with its paper on Daily Papers page.

#1 opened 12 days ago by

AdinaY

commented 2 papers 12 days ago

EMMA: Your Text-to-Image Diffusion Model Can Secretly Accept Multi-Modal Prompts

Paper • 2406.09412 • Published 13 days ago • 10 •

Explore the Limits of Omni-modal Pretraining at Scale

Paper • 2406.08707 • Published 14 days ago • 14 •

New activity in Yiyuan/MiCo-ViT-g-14-omnimodal-300k-b64K 12 days ago

Add paper link to connect the model to its paper on Daily Papers page

#1 opened 12 days ago by

AdinaY

commented a paper 12 days ago

mOSCAR: A Large-scale Multilingual and Multimodal Document-level Corpus

New activity in llm-council/emotional_application 12 days ago

Add paper link to connect dataset to its paper on Daily Papers page

Paper • 2406.09411 • Published 13 days ago • 17 •

#2 opened 12 days ago by

AdinaY

New activity in CommonsenseT2I/CommonsensenT2I 12 days ago

add paper link to connect dataset to its paper on Daily Papers page

#2 opened 12 days ago by

AdinaY

New activity in baharef/ToT 12 days ago

add paper link to connect the dataset to its paper on Daily Papers page

#2 opened 12 days ago by

AdinaY

commented a paper 12 days ago

MuirBench: A Comprehensive Benchmark for Robust Multi-image Understanding

Paper • 2406.09414 • Published 13 days ago • 86 •

New activity in MUIRBENCH/MUIRBENCH 12 days ago

Add paper link to connect dataset to its paper on Daily Papers page

#2 opened 12 days ago by

AdinaY

commented 2 papers 12 days ago

Depth Anything V2

12

PowerInfer-2: Fast Large Language Model Inference on a Smartphone

Paper • 2406.06282 • Published 16 days ago • 34 •

5

commented 2 papers 13 days ago

Turbo Sparse: Achieving LLM SOTA Performance with Minimal Activated Parameters

Paper • 2406.05955 • Published 17 days ago • 21 •

Paper • 2406.05132 • Published 19 days ago • 27 •

3D-GRAND: A Million-Scale Dataset for 3D-LLMs with Better Grounding and Less Hallucination

Paper • 2406.06563 • Published 24 days ago • 17 •

commented 2 papers 14 days ago

Skywork-MoE: A Deep Dive into Training Techniques for Mixture-of-Experts Language Models

10

4Real: Towards Photorealistic 4D Scene Generation via Video Diffusion Models

Paper • 2406.07472 • Published 15 days ago • 10 •

Paper • 2406.07524 • Published 15 days ago • 7 •

New activity in Skywork/Skywork-MoE-Base 14 days ago

Add paper link to connect the model to its paper on Daily Papers page

#3 opened 14 days ago by

AdinaY

commented a paper 14 days ago

Simple and Effective Masked Diffusion Language Models

Paper • 2406.01493 • Published 23 days ago • 17 •

New activity in kuleshov-group/mdlm-owt 14 days ago

Add paper link to connect the model with its paper on Daily Papers page

#1 opened 14 days ago by

AdinaY

New activity in xichenhku/MimicBrush 14 days ago

Add paper link to connect the demo to its paper on Daily Papers page.

#3 opened 14 days ago by

AdinaY

commented 3 papers 15 days ago

Learning Temporally Consistent Video Depth from Video Diffusion Priors

Paper • 2406.06525 • Published 16 days ago • 60 •

Autoregressive Model Beats Diffusion: Llama for Scalable Image Generation