activity
20242026
collaborators

28 papers

cs.LG2026

HP-JEPA: Hierarchical Partitioning for Multi-Resolution Graph Joint-Embedding Predictive Learning

Ruichen Xu, Jingxiang Qu, Wenhan Gao +5

Graph self-supervised learning aims to learn transferable representations from large-scale unlabeled graph data. Joint-embedding predictive architectures (JEPAs) avoid explicit neg…

cs.CL2026

You Had One Job: Per-Task Quantization Using LLMs' Hidden Representations

Amit LeVi, Raz Lapid, Rom Himelstein +3

Many LLM applications require only narrow capabilities, yet standard post-training quantization (PTQ) methods allocate precision without considering the target task. This can waste…

cs.SD2026

S-JEPA : Soft Clustering Anchors for Self-Supervised Speech Representation Learning

Georgios Ioannides, Adrian Kieback, Judah Goldfeder +5

Self-supervised speech encoders are predominantly trained by predicting discrete hard cluster IDs at masked positions, a recipe that collapses acoustic ambiguity at category bounda…

cs.CV2026

Mirage Probes: How Vision Models Fake Visual Understanding

Daniel Ben-Levi, Judah Goldfeder, Weiliang Zhao +5

Vision-language models (VLMs) can answer image-based questions confidently, and often correctly, even when no image is provided. This mirage behavior inflates benchmark scores with…

cs.LG2026

On Training in Imagination

Nadav Timor, Ravid Shwartz-Ziv, Micah Goldblum +2

State-of-the-art model-based reinforcement learning methods train policies on imagined rollouts. These rollouts are trajectories generated by a learned dynamics model and are score…

cs.AI2026

Measure what Matters: Psychometric Evaluation of AI with Situational Judgment Tests

Alexandra Yost, Shreyans Jain, Shivam Raval +6

Persona conditioning is widely used to steer large language model (LLM) behavior, but it is unclear whether it induces stable behavioral structure or superficial variation. We prop…