1 | Ravid Shwartz-Ziv

Mirage Probes: How Vision Models Fake Visual Understanding

Thu, 11 Jun 2026 19:51:44 +0000

JEPA as a Neural Tokenizer: Learning Robust Speech Representations with Density Adaptive Attention

Mon, 08 Dec 2025 00:00:00 +0000

A superpersuasive autonomous policy debating system

Sat, 22 Nov 2025 00:45:01 +0000

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

Sun, 09 Nov 2025 19:58:24 +0000

The workshop version is identified in the arXiv record. The original preprint was released in November 2025; the latest revision was submitted in June 2026.

Exploring Human-AI Conceptual Alignment through the Prism of Chess

Wed, 29 Oct 2025 00:00:00 +0000

Antislop: A Comprehensive Framework for Identifying and Eliminating Repetitive Patterns in Language Models

Thu, 16 Oct 2025 18:22:22 +0000

Attention Sinks and Compression Valleys in LLMs are Two Sides of the Same Coin

Tue, 07 Oct 2025 21:27:24 +0000

The Illusion of Progress: Re-evaluating Hallucination Detection in LLMs

Fri, 01 Aug 2025 20:34:01 +0000

Layer by Layer: Uncovering Hidden Representations in Language Models

Sun, 13 Jul 2025 00:00:00 +0000

Layer Importance for Mathematical Reasoning is Forged in Pre-Training and Invariant after Post-Training

Fri, 27 Jun 2025 21:04:55 +0000

From Tokens to Thoughts: How LLMs and Humans Trade Compression for Meaning

Wed, 21 May 2025 16:29:00 +0000

Fine-Tuning with Uncertainty-Aware Priors Makes Vision and Language Foundation Models More Reliable

Sat, 03 May 2025 00:00:00 +0000

Rate-In: Information-Driven Adaptive Dropout Rates for Improved Inference-Time Uncertainty Estimation

Tue, 10 Dec 2024 04:03:46 +0000

Seq-VCR: Preventing Collapse in Intermediate Transformer Representations for Enhanced Reasoning

Mon, 04 Nov 2024 00:00:00 +0000

Turning Up the Heat: Min-p Sampling for Creative and Coherent LLM Outputs

Mon, 01 Jul 2024 00:00:00 +0000

Presented at ICLR 2025 (Oral). First released in July 2024; the latest arXiv revision is from November 2025.

LiveBench: A Challenging, Contamination-Limited LLM Benchmark

Thu, 27 Jun 2024 00:00:00 +0000

OpenDebateEvidence: A Massive-Scale Argument Mining and Summarization Dataset

Thu, 20 Jun 2024 00:00:00 +0000

An Information Theory Perspective on Variance-Invariance-Covariance Regularization

Fri, 15 Dec 2023 00:00:00 +0000

Volume: 36 Pages: 33965-33998 [Published in NeurIPS 2023]

Back to Basics: Revisiting Standard Deep Learning Components for Class Imbalance

Mon, 11 Dec 2023 00:00:00 +0000

[Published in NeurIPS 2023]

What Do We Maximize in Self-Supervised Learning?

Mon, 01 Aug 2022 00:00:00 +0000

Pre-Train Your Loss: Easy Bayesian Transfer Learning with Informative Priors

Sun, 01 May 2022 00:00:00 +0000

Information in Infinite Ensembles of Infinitely-Wide Neural Networks

Wed, 01 Jan 2020 00:00:00 +0000

Attentioned Convolutional LSTM Inpaintingv Network for Anomaly Detection in Videos

Sat, 01 Dec 2018 00:00:00 +0000

Tabular Data: Deep Learning is Not All You Need

Sun, 01 Jan 2017 00:00:00 +0000

Automated Testing of Graphics Units by Deep-Learning Detection of Visual Anomalies

Mon, 01 Jan 0001 00:00:00 +0000