jasonjiang

mikinyaa's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted a paper about 23 hours ago

CASA: Cross-Attention via Self-Attention for Efficient Vision-Language Fusion

Paper • 2512.19535 • Published 5 days ago • 8

upvoted a paper about 24 hours ago

TurboDiffusion: Accelerating Video Diffusion Models by 100-200 Times

Paper • 2512.16093 • Published 9 days ago • 64

upvoted 2 papers 3 days ago

The Prism Hypothesis: Harmonizing Semantic and Pixel Representations via Unified Autoencoding

Paper • 2512.19693 • Published 4 days ago • 60

DataFlow: An LLM-Driven Framework for Unified Data Preparation and Workflow Automation in the Era of Data-Centric AI

Paper • 2512.16676 • Published 9 days ago • 188

upvoted a paper 4 days ago

Probing Scientific General Intelligence of LLMs with Scientist-Aligned Workflows

Paper • 2512.16969 • Published 9 days ago • 105

upvoted 2 papers 8 days ago

HyperVL: An Efficient and Dynamic Multimodal Large Language Model for Edge Devices

Paper • 2512.14052 • Published 11 days ago • 39

Are We Ready for RL in Text-to-3D Generation? A Progressive Investigation

Paper • 2512.10949 • Published 15 days ago • 45

upvoted 2 papers 10 days ago

Towards Scalable Pre-training of Visual Tokenizers for Generation

Paper • 2512.13687 • Published 11 days ago • 95

ReFusion: A Diffusion Large Language Model with Parallel Autoregressive Decoding

Paper • 2512.13586 • Published 11 days ago • 87

upvoted a paper 11 days ago

Sliding Window Attention Adaptation

Paper • 2512.10411 • Published 16 days ago • 17

upvoted a paper 15 days ago

StereoWorld: Geometry-Aware Monocular-to-Stereo Video Generation

Paper • 2512.09363 • Published 17 days ago • 70

upvoted a paper 18 days ago

PaperDebugger: A Plugin-Based Multi-Agent System for In-Editor Academic Writing, Review, and Editing

Paper • 2512.02589 • Published 25 days ago • 63

upvoted 6 papers 22 days ago

ToolOrchestra: Elevating Intelligence via Efficient Model and Tool Orchestration

Paper • 2511.21689 • Published about 1 month ago • 109

Qwen3-VL Technical Report

Paper • 2511.21631 • Published about 1 month ago • 140

Harmony: Harmonizing Audio and Video Generation through Cross-Task Synergy

Paper • 2511.21579 • Published about 1 month ago • 23

Multimodal Evaluation of Russian-language Architectures

Paper • 2511.15552 • Published Nov 19 • 78

ENACT: Evaluating Embodied Cognition with World Modeling of Egocentric Interaction

Paper • 2511.20937 • Published Nov 26 • 15

MIRA: Multimodal Iterative Reasoning Agent for Image Editing

Paper • 2511.21087 • Published about 1 month ago • 10

upvoted 2 papers 24 days ago

Infinity-RoPE: Action-Controllable Infinite Video Generation Emerges From Autoregressive Self-Rollout

Paper • 2511.20649 • Published Nov 25 • 45

DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models

Paper • 2512.02556 • Published 25 days ago • 234