刘奕辰

ScarlettJackson's activity

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

upvoted a paper about 8 hours ago

SpanCalib-VLM: Calibrated Hallucination Span Detection in Vision-Language Models

Paper • 2608.29974 • Published 5 days ago • 5

liked a dataset 22 days ago

pluslab/PLUS_Lab_GPUs_Data

Updated 1 minute ago • 17.2k • 24

upvoted 3 papers about 1 month ago

Human-in-the-Loop Signature Bootstrapping for UAV Hyperspectral PFM-1 Mine Detection

Paper • 2607.25310 • Published Jul 28 • 5

Mental World Modeling

Paper • 2607.27201 • Published Jul 29 • 109

CoRT: Counterfactual Replay for Token-Level Rubric-Guided Policy Optimization

Paper • 2607.25659 • Published Jul 28 • 84

liked a dataset about 1 month ago

StannumX/0930ae

Updated 6 minutes ago • 12k • 11

upvoted 3 papers about 1 month ago

Tencent WorkBuddy Bench: A Multi-Domain Coding-Agent Benchmark with Contamination-Resistant Task Construction

Paper • 2607.20911 • Published Jul 23 • 26

RynnBrain 1.1: Towards More Capable and Generalizable Embodied Foundation Model

Paper • 2607.17977 • Published Jul 20 • 198

Loop the Loopies!

Paper • 2607.16051 • Published Jul 17 • 77

liked a dataset about 2 months ago

hf-doc-build/doc-build-dev

Updated Apr 20 • 1.18M • 53

upvoted 2 papers about 2 months ago

LongStraw: Long-Context RL Beyond 2M Tokens under a Fixed GPU Budget

Paper • 2607.14952 • Published Jul 16 • 212

Metacognition in LLMs: Foundations, Progress, and Opportunities

Paper • 2607.11881 • Published Jul 13 • 30

liked a model about 2 months ago

BAAI/bge-base-en-v1.5

Feature Extraction • 0.1B • Updated Feb 21, 2024 • 11.2M • • 469

upvoted 2 papers about 2 months ago

Function-Aware Fill-in-the-Middle as Mid-Training for Coding Agent Foundation Models

Paper • 2607.12463 • Published Jul 14 • 108

Read It Back: Pretrained MLLMs Are Zero-Shot Reward Models for Text-to-Image Generation

Paper • 2607.11886 • Published Jul 13 • 86

liked a model about 2 months ago

uzumix/krea2_herpov

Text-to-Image • Updated Jul 7 • 126 • • 3

upvoted 2 papers about 2 months ago

OmniOpt: Taxonomy, Geometry, and Benchmarking of Modern Optimizers

Paper • 2607.04033 • Published Jul 4 • 77

Mind the Heads: Topological Representation Alignment for Multimodal LLMs

Paper • 2606.23885 • Published Jun 22 • 5

liked a dataset 2 months ago

penfever/terminal_bench_2_exp_psu_swesmith_1K_glm_4_7_traces_jupiter__4_0__Qwen3_8B_20264b24e003

Viewer • Updated Jul 3 • 2.73k • 19 • 1

upvoted a paper 2 months ago

Escaping the Self-Confirmation Trap: An Execute-Distill-Verify Paradigm for Agentic Experience Learning

Paper • 2606.24428 • Published Jun 23 • 52