Basil Cheer

basilcheer's activity

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

upvoted a paper about 23 hours ago

Bridging Semantic and Kinematic Conditions with Diffusion-based Discrete Motion Tokenizer

Paper • 2603.19227 • Published 4 days ago • 40

upvoted 19 papers 1 day ago

LaDe: Unified Multi-Layered Graphic Media Generation and Decomposition

Paper • 2603.17965 • Published 5 days ago • 5

Cubic Discrete Diffusion: Discrete Visual Generation on High-Dimensional Representation Tokens

Paper • 2603.19232 • Published 4 days ago • 31

Efficient Training-Free Multi-Token Prediction via Embedding-Space Probing

Paper • 2603.17942 • Published 5 days ago • 5

FASTER: Rethinking Real-Time Flow VLAs

Paper • 2603.19199 • Published 4 days ago • 51

BenchPreS: A Benchmark for Context-Aware Personalized Preference Selectivity of Persistent-Memory LLMs

Paper • 2603.16557 • Published 6 days ago • 20

Alignment Makes Language Models Normative, Not Descriptive

Paper • 2603.17218 • Published 5 days ago • 45

AdaMem: Adaptive User-Centric Memory for Long-Horizon Dialogue Agents

Paper • 2603.16496 • Published 6 days ago • 12

SocialOmni: Benchmarking Audio-Visual Social Interactivity in Omni Models

Paper • 2603.16859 • Published 6 days ago • 241

Rethinking UMM Visual Generation: Masked Modeling for Efficient Image-Only Pre-training

Paper • 2603.16139 • Published 6 days ago • 31

Qianfan-OCR: A Unified End-to-End Model for Document Intelligence

Paper • 2603.13398 • Published 12 days ago • 143

Safe and Scalable Web Agent Learning via Recreated Websites

Paper • 2603.10505 • Published 12 days ago • 25

AgentProcessBench: Diagnosing Step-Level Process Quality in Tool-Using Agents

Paper • 2603.14465 • Published 8 days ago • 22

GLM-5: from Vibe Coding to Agentic Engineering

Paper • 2602.15763 • Published Feb 17 • 116

HSImul3R: Physics-in-the-Loop Reconstruction of Simulation-Ready Human-Scene Interactions

Paper • 2603.15612 • Published 7 days ago • 149

OpenSeeker: Democratizing Frontier Search Agents by Fully Open-Sourcing Training Data

Paper • 2603.15594 • Published 7 days ago • 141

Cheers: Decoupling Patch Details from Semantic Representations Enables Unified Multimodal Comprehension and Generation

Paper • 2603.12793 • Published 10 days ago • 37

One Model, Many Budgets: Elastic Latent Interfaces for Diffusion Transformers

Paper • 2603.12245 • Published 11 days ago • 18

Video-Based Reward Modeling for Computer-Use Agents

Paper • 2603.10178 • Published 13 days ago • 42

WeEdit: A Dataset, Benchmark and Glyph-Guided Framework for Text-centric Image Editing

Paper • 2603.11593 • Published 11 days ago • 25