Xiaoya Lu

Ursulalala's activity

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

upvoted 2 papers 2 days ago

Vlaser: Vision-Language-Action Model with Synergistic Embodied Reasoning

Paper • 2510.11027 • Published 5 days ago • 17

High-Fidelity Simulated Data Generation for Real-World Zero-Shot Robotic Manipulation Learning with Gaussian Splatting

Paper • 2510.10637 • Published 6 days ago • 11

upvoted a paper 4 days ago

BEAR: Benchmarking and Enhancing Multimodal Language Models for Atomic Embodied Capabilities

Paper • 2510.08759 • Published 9 days ago • 44

upvoted a paper 8 days ago

LLMs Learn to Deceive Unintentionally: Emergent Misalignment in Dishonesty from Misaligned Samples to Biased Human-AI Interactions

Paper • 2510.08211 • Published 9 days ago • 22

upvoted a paper 18 days ago

Taming Masked Diffusion Language Models via Consistency Trajectory Reinforcement Learning with Fewer Decoding Step

Paper • 2509.23924 • Published 20 days ago • 7

upvoted a paper 23 days ago

How Far are VLMs from Visual Spatial Intelligence? A Benchmark-Driven Perspective

Paper • 2509.18905 • Published 25 days ago • 28

upvoted a paper 2 months ago

SSRL: Self-Search Reinforcement Learning

Paper • 2508.10874 • Published Aug 14 • 94

upvoted 5 papers 3 months ago

Frontier AI Risk Management Framework in Practice: A Risk Analysis Technical Report

Paper • 2507.16534 • Published Jul 22 • 7

The Devil behind the mask: An emergent safety vulnerability of Diffusion LLMs

Paper • 2507.11097 • Published Jul 15 • 64

IS-Bench: Evaluating Interactive Safety of VLM-Driven Embodied Agents in Daily Household Tasks

Paper • 2506.16402 • Published Jun 19 • 1

X-Boundary: Establishing Exact Safety Boundary to Shield LLMs from Multi-Turn Jailbreaks without Compromising Usability

Paper • 2502.09990 • Published Feb 14 • 1

Derail Yourself: Multi-turn LLM Jailbreak Attack through Self-discovered Clues

Paper • 2410.10700 • Published Oct 14, 2024 • 3

authored 3 papers 3 months ago

IS-Bench: Evaluating Interactive Safety of VLM-Driven Embodied Agents in Daily Household Tasks

Paper • 2506.16402 • Published Jun 19 • 1

Derail Yourself: Multi-turn LLM Jailbreak Attack through Self-discovered Clues

Paper • 2410.10700 • Published Oct 14, 2024 • 3

X-Boundary: Establishing Exact Safety Boundary to Shield LLMs from Multi-Turn Jailbreaks without Compromising Usability

Paper • 2502.09990 • Published Feb 14 • 1

updated a dataset 3 months ago

Ursulalala/IS_Bench_dataset

Viewer • Updated Jul 14 • 6.06k • 50

published a dataset 3 months ago

Ursulalala/IS_Bench_dataset

Viewer • Updated Jul 14 • 6.06k • 50

upvoted a paper 7 months ago

Position: Interactive Generative Video as Next-Generation Game Engine

Paper • 2503.17359 • Published Mar 21 • 61

updated a collection 7 months ago

X-Boundary

Collection

The models of the paper "X-Boundary: Establishing Exact Safety Boundary to Shield LLMs from Multi-Turn Jailbreaks without Compromising Usability". • 4 items • Updated Mar 11 • 2