Zhu Xiangyang

yyy127's activity

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

submitted a paper to Daily Papers 1 day ago

Emergent Misalignment Can Be Induced by Sycophancy and Reversed via Alignment Gating

Paper • 2606.09068 • Published 3 days ago • 4

authored 13 papers 2 days ago

Point-Bind & Point-LLM: Aligning Point Cloud with Multi-modality for 3D Understanding, Generation, and Instruction Following

Paper • 2309.00615 • Published Sep 1, 2023 • 13

PointCLIP V2: Prompting CLIP and GPT for Powerful 3D Open-world Learning

Paper • 2211.11682 • Published Nov 21, 2022

Lumina-Next: Making Lumina-T2X Stronger and Faster with Next-DiT

Paper • 2406.18583 • Published Jun 5, 2024

SAM2Point: Segment Any 3D as Videos in Zero-shot and Promptable Manners

Paper • 2408.16768 • Published Aug 29, 2024 • 28

Lumina-Image 2.0: A Unified and Efficient Image Generative Framework

Paper • 2503.21758 • Published Mar 27, 2025 • 22

VQAThinker: Exploring Generalizable and Explainable Video Quality Assessment via Reinforcement Learning

Paper • 2508.06051 • Published Aug 8, 2025

SafetyFlow: An Agent-Flow System for Automated LLM Safety Benchmarking

Paper • 2508.15526 • Published Aug 21, 2025

Embodied Image Compression

Paper • 2512.11612 • Published Dec 12, 2025 • 1

SafeSci: Safety Evaluation of Large Language Models in Science Domains and Beyond

Paper • 2603.01589 • Published Mar 2

One Battle After Another: Probing LLMs' Limits on Multi-Turn Instruction Following with a Benchmark Evolving Framework

Paper • 2511.03508 • Published Jan 8

Generalizable Video Quality Assessment via Weak-to-Strong Learning

Paper • 2505.03631 • Published 18 days ago

Emergent Misalignment Can Be Induced by Sycophancy and Reversed via Alignment Gating

Paper • 2606.09068 • Published 3 days ago • 4

Not All Features Matter: Enhancing Few-shot CLIP with Adaptive Prior Refinement

Paper • 2304.01195 • Published Apr 3, 2023

upvoted a paper 2 days ago

Emergent Misalignment Can Be Induced by Sycophancy and Reversed via Alignment Gating

Paper • 2606.09068 • Published 3 days ago • 4

upvoted a paper about 2 months ago

Emergent Social Intelligence Risks in Generative Multi-Agent Systems

Paper • 2603.27771 • Published Mar 29 • 52

updated a dataset 2 months ago

yyy127/SafeSci

Preview • Updated Apr 3 • 30 • 2

updated 3 models 3 months ago

yyy127/Qwen3-14B-SafeSci-LoRA

15B • Updated Mar 4 • 2

yyy127/Llama-3.1-8B-SafeSci-LoRA

8B • Updated Mar 4

yyy127/Qwen3-8B-SafeSci-LoRA

8B • Updated Mar 4 • 1