The Hong Kong Polytechnic University

The Hong Kong Polytechnic University on Hugging Face Daily Papers: 24 papers, 1 in the top 3 of their day, 0 paper of the day.

  1. Lab2Sim: Turning Real-World Experiment Videos into Interactive Virtual Experiments 4 upvotes, #42 of 2026-11-03
  2. OSWAM: An Effective World Action Model with One-Step Action Generation 9 upvotes, #19 of 2026-11-02
  3. When Does Dense Retrieval Need Asymmetric Geometry? A Bias-Variance Theory of Shared and Dual Projections 26 upvotes, #37 of 2026-09-30
  4. Org-Agent: Beyond Personal Assistants Towards Organizational Agents 6 upvotes, #68 of 2026-09-30
  5. Routing Drift Alone Does Not Diagnose Failure in Merged MoE LLMs 5 upvotes, #64 of 2026-09-29
  6. SMAT: Simple and Efficient Merge-Aware Training 5 upvotes, #64 of 2026-09-29
  7. RelightFormer: Feed-forward Generative Transformer for Multiview Object Relighting 14 upvotes, #42 of 2026-09-09
  8. Persistent Recursive Worlds Enable Autonomous Software Evolution 6 upvotes, #16 of 2026-08-13
  9. SAE Interventions are Unreliable: Post-Intervention Recovery of Suppressed Behavior 17 upvotes, #8 of 2026-06-18
  10. BadWorld: Adversarial Attacks on World Models 18 upvotes, #11 of 2026-06-16
  11. Access Sets Matter: Budgeting Expert Reads for Scalable Weight-Space Model Merging 4 upvotes, #32 of 2026-06-04
  12. Not All Disagreement Is Learnable: Token Teachability in On-Policy Distillation 26 upvotes, #16 of 2026-06-01
  13. E-PMQ: Expert-Guided Post-Merge Quantization with Merged-Weight Anchoring 2 upvotes, #45 of 2026-05-19
  14. FeatCal: Feature Calibration for Post-Merging Models 7 upvotes, #25 of 2026-05-14
  15. Model Merging Scaling Laws in Large Language Models 44 upvotes, #6 of 2026-05-12
  16. Geometry Conflict: Explaining and Controlling Forgetting in LLM Continual Post-Training 50 upvotes, #4 of 2026-05-12
  17. ShadowPEFT: Shadow Network for Parameter-Efficient Fine-Tuning 28 upvotes, #7 of 2026-04-22
  18. Multiscale Switch for Semi-Supervised and Contrastive Learning in Medical Ultrasound Image Segmentation 2 upvotes, #30 of 2026-03-23
  19. DARE: Aligning LLM Agents with the R Statistical Ecosystem via Distribution-Aware Retrieval 47 upvotes, #3 of 2026-03-06
  20. CL4SE: A Context Learning Benchmark For Software Engineering Tasks 2 upvotes, #20 of 2026-03-02
  21. Pretraining A Large Language Model using Distributed GPUs: A Memory-Efficient Decentralized Paradigm 4 upvotes, #30 of 2026-02-13
  22. DSAEval: Evaluating Data Science Agents on a Wide Range of Real-World Data Science Problems 2 upvotes, #28 of 2026-01-21
  23. DeContext as Defense: Safe Image Editing in Diffusion Transformers 24 upvotes, #11 of 2025-12-19
  24. SCALE: Selective Resource Allocation for Overcoming Performance Bottlenecks in Mathematical Test-time Scaling 8 upvotes, #23 of 2025-12-02

Data: hysts-bot-data/daily-papers-stats and the Daily Papers API. Open data: tardellirs/paper-pulse-data. Sister project: Model Pulse, the download history of every model on the Hub.