pith. sign in

Ruoxi Jia

Identifiers

  • name variant Ruoxi Jia 0.60 · backfill

Papers (16)

  1. Memory-Induced Tool-Drift in LLM Agents cs.CR · 2026 · author #4
  2. Remembering More, Risking More: Longitudinal Safety Risks in Memory-Equipped LLM Agents cs.AI · 2026 · author #4
  3. Confidence-Aware Alignment Makes Reasoning LLMs More Reliable cs.AI · 2026 · author #8
  4. Mitigating Many-shot Jailbreak Attacks with One Single Demonstration cs.CR · 2026 · author #8
  5. Characterizing Model-Native Skills cs.AI · 2026 · author #4
  6. Can Small Training Runs Reliably Guide Data Curation? Rethinking Proxy-Model Practice cs.LG · 2025 · author #6
  7. The Signal is in the Steps: Local Scoring for Reasoning Data Selection cs.LG · 2025 · author #3
  8. Injecting Measurement Information Yields a Fast and Noise-Robust Diffusion-Based Inverse Problem Solver cs.LG · 2025 · author #4
  9. Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety cs.CR · 2025 · author #36
  10. Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To! cs.CL · 2023 · author #5
  11. One Bit Matters: Understanding Adversarial Examples as the Abuse of Redundancy cs.LG · 2018 · author #2
  12. The Helmholtz Method: Using Perceptual Compression to Reduce Machine Learning Complexity cs.CV · 2018 · author #3
  13. Privacy-Enhanced Architecture for Occupancy-based HVAC Control cs.CR · 2016 · author #1
  14. SoundLoc: Acoustic Method for Indoor Localization without Infrastructure cs.HC · 2014 · author #1
  15. PresenceSense: Zero-training Algorithm for Individual Presence Detection based on Power Monitoring cs.HC · 2014 · author #2
  16. Environmental Sensing by Wearable Device for Indoor Activity and Location Estimation cs.HC · 2014 · author #4

Mentions

  • 2605.24941 #4 · arxiv_oai · confidence 0.70 Ruoxi Jia
  • 2605.17830 #4 · arxiv_oai · confidence 0.70 Ruoxi Jia

Frequent Coauthors