The Hong Kong Polytechnic University

university

Verified

https://www.polyu.edu.hk/

Activity Feed Request to join this org

AI & ML interests

None defined yet.

Recent Activity

adamdad submitted a paper 24 days ago

SAE Interventions are Unreliable: Post-Intervention Recovery of Suppressed Behavior

adamdad submitted a paper 26 days ago

BadWorld: Adversarial Attacks on World Models

wyy-code submitted a paper about 1 month ago

Not All Disagreement Is Learnable: Token Teachability in On-Policy Distillation

View all activity

Papers

SAE Interventions are Unreliable: Post-Intervention Recovery of Suppressed Behavior

BadWorld: Adversarial Attacks on World Models

View all Papers

sslu

authored 3 papers 13 days ago

Geometry Conflict: Explaining and Controlling Forgetting in LLM Continual Post-Training

Paper • 2605.09608 • Published May 10 • 53

Not All Disagreement Is Learnable: Token Teachability in On-Policy Distillation

Paper • 2605.26844 • Published May 26 • 26

Access Sets Matter: Budgeting Expert Reads for Scalable Weight-Space Model Merging

Paper • 2605.29489 • Published May 28 • 4

authored 2 papers 24 days ago

DeContext as Defense: Safe Image Editing in Diffusion Transformers

Paper • 2512.16625 • Published Dec 18, 2025 • 25

BadWorld: Adversarial Attacks on World Models

Paper • 2606.16519 • Published 27 days ago • 18

submitted a paper to Daily Papers 24 days ago

SAE Interventions are Unreliable: Post-Intervention Recovery of Suppressed Behavior

Paper • 2606.18322 • Published 26 days ago • 17

authored 3 papers 26 days ago

Dialogue Language Model with Large-Scale Persona Data Engineering

Paper • 2412.09034 • Published Dec 12, 2024

InfantCryNet: A Data-driven Framework for Intelligent Analysis of Infant Cries

Paper • 2409.19689 • Published Sep 29, 2024 • 1

UXBench: Benchmarking User Experience in AI Assistants

Paper • 2606.09570 • Published Jun 8 • 4

submitted a paper to Daily Papers 26 days ago

BadWorld: Adversarial Attacks on World Models

Paper • 2606.16519 • Published 27 days ago • 18

authored a paper about 1 month ago

Beyond APIs: Probing the Limits of MLLMs in Physical Tool Use

Paper • 2606.10803 • Published Jun 9 • 2

submitted a paper to Daily Papers about 1 month ago

Not All Disagreement Is Learnable: Token Teachability in On-Policy Distillation

Paper • 2605.26844 • Published May 26 • 26

submitted a paper to Daily Papers about 1 month ago

ORACLE: Anticipating Scams from Partial Trajectories in Streaming App Usage

Paper • 2605.16363 • Published May 9 • 1

authored a paper about 1 month ago

ORACLE: Anticipating Scams from Partial Trajectories in Streaming App Usage

Paper • 2605.16363 • Published May 9 • 1

submitted a paper to Daily Papers about 2 months ago

E-PMQ: Expert-Guided Post-Merge Quantization with Merged-Weight Anchoring

Paper • 2605.16882 • Published May 16 • 2

submitted a paper to Daily Papers about 2 months ago

FeatCal: Feature Calibration for Post-Merging Models

Paper • 2605.13030 • Published May 13 • 7

submitted a paper to Daily Papers 2 months ago

Model Merging Scaling Laws in Large Language Models

Paper • 2509.24244 • Published May 11 • 44

submitted a paper to Daily Papers 3 months ago

ShadowPEFT: Shadow Network for Parameter-Efficient Fine-Tuning

Paper • 2604.19254 • Published Apr 21 • 30

submitted a paper to Daily Papers 3 months ago

On Semiotic-Grounded Interpretive Evaluation of Generative Art

Paper • 2604.08641 • Published Apr 9 • 4

submitted a paper to Daily Papers 4 months ago

Multiscale Switch for Semi-Supervised and Contrastive Learning in Medical Ultrasound Image Segmentation

Paper • 2603.18655 • Published Mar 19 • 2