OpenReview.net

Login

Back to ICLR

ICLR 2026 Workshop Sci4DL Submissions

Loading

About OpenReview
Hosting a Venue
All Venues

Contact
Sponsors
Donate

FAQ
Terms of Use / Privacy Policy
News

About OpenReview
Hosting a Venue
All Venues
Sponsors
News

FAQ
Contact
Donate
Terms of Use
Privacy Policy

OpenReview is a long-term project to advance science through improved peer review with legal nonprofit status. We gratefully acknowledge the support of the OpenReview Sponsors. © 2026 OpenReview

Transformers are Optimal Effective Fields
ICLR 2026 Workshop Sci4DL Submission122 Authors
- 05 Feb 2026 (modified: 02 Mar 2026)
- Submitted to Sci4DL 2026
- Readers: Everyone
Modeling Tool Use in Transformers via Computation Oracles
ICLR 2026 Workshop Sci4DL Submission121 Authors
- 05 Feb 2026 (modified: 02 Mar 2026)
- Submitted to Sci4DL 2026
- Readers: Everyone
From Perfect AUC to Poor Transfer: Diagnosing Leakage in Cross-Platform Gene Signature Learning
ICLR 2026 Workshop Sci4DL Submission120 Authors
- 05 Feb 2026 (modified: 02 Mar 2026)
- Submitted to Sci4DL 2026
- Readers: Everyone
Learning When to Be Sparse: Adaptive Activations via Two-Parameter Entropy
Roman Rudamenko, Dmitry Abulkhanov, Konstantin Semenov, Michael Diskin, Alexander Savchenko
- Published: 02 Mar 2026, Last Modified: 25 Apr 2026
- Sci4DL 2026
- Readers: Everyone
Unified Perspectives on Balancedness and Parameter-norm Evolution in Neural Nets
Jasraj Singh, Enea Monzio Compagnoni, Antonio Orvieto
- Published: 02 Mar 2026, Last Modified: 08 May 2026
- Sci4DL 2026
- Readers: Everyone
Sustained Gradient Alignment Mediates Subliminal Learning in a Multi-Step Setting: Evidence from MNIST Auxiliary Logit Distillation Experiment
Chayanon Kitkana, Shivam Arora
- Published: 02 Mar 2026, Last Modified: 21 Apr 2026
- Sci4DL 2026
- Readers: Everyone
Physics-Aligned Decoding (PAD) for Discrete Protein Structure Representations
ICLR 2026 Workshop Sci4DL Submission116 Authors
- 05 Feb 2026 (modified: 02 Mar 2026)
- Submitted to Sci4DL 2026
- Readers: Everyone
Identifying Geometric Bottlenecks in Single-Stage Training: Observations from the Optimization Manifold
ICLR 2026 Workshop Sci4DL Submission115 Authors
- 05 Feb 2026 (modified: 02 Mar 2026)
- Submitted to Sci4DL 2026
- Readers: Everyone
Entropy-Lens: Uncovering Decision Strategies in LLMs
Christopher Irwin, Francesco Caso, Riccardo Ali, Pietro Lio
- Published: 02 Mar 2026, Last Modified: 02 Mar 2026
- Sci4DL 2026
- Readers: Everyone
Shared Gradient Discovery and Superposition: Learning Dynamics of Generalization in LLMs
Andrei Mircea, Ildus Sadrtdinov, Irina Rish, Ekaterina Lobacheva
- Published: 02 Mar 2026, Last Modified: 25 Apr 2026
- Sci4DL 2026
- Readers: Everyone
Deriving Hyperparameter Scaling Laws via Modern Optimization Theory
Egor Shulgin, Dimitri von Rütte, Tianyue H. Zhang, Niccolò Ajroldi, Bernhard Schölkopf, Antonio Orvieto
- Published: 02 Mar 2026, Last Modified: 16 Mar 2026
- Sci4DL 2026
- Readers: Everyone
All in the Head?: A Controlled Study of Component Contributions in Few-Shot NLP
Rishaan Desai
- Published: 02 Mar 2026, Last Modified: 02 Mar 2026
- Sci4DL 2026
- Readers: Everyone
STRIDE: Training Data Attribution Can Be Estimated In Activation Space
Abir HARRASSE, Rishit Dagli, Amir Abdullah, Zhijing Jin
- Published: 02 Mar 2026, Last Modified: 02 Apr 2026
- Sci4DL 2026
- Readers: Everyone
Geometric Stability of Representation Manifolds as a Training-Free Diagnostic for Studying Data Augmentations
Ahmad Taha, Rustam A. Lukmanov
- Published: 02 Mar 2026, Last Modified: 02 Mar 2026
- Sci4DL 2026
- Readers: Everyone
Pretraining with Masked Backstories in a Toy World
Sultan Daniels, Dylan Davis, Gireeja Ranade, Anant Sahai
- Published: 02 Mar 2026, Last Modified: 03 Mar 2026
- Sci4DL 2026
- Readers: Everyone
Optimal scaling laws in learning hierarchical multi-index models
Leonardo Defilippis, Florent Krzakala, Bruno Loureiro, Antoine Maillard
- Published: 02 Mar 2026, Last Modified: 12 May 2026
- Sci4DL 2026
- Readers: Everyone
Dropout and the Outliers: Could Transformers Overcome Their Single Points of Failure?
Nour Hezbri, Gilles Bareilles, El-Mahdi El-Mhamdi
- Published: 02 Mar 2026, Last Modified: 11 May 2026
- Sci4DL 2026
- Readers: Everyone
Revealing Task-Dependent Layer Relevance via Attentive Multi-Layer Fusion
Marco Morik, Laure Ciernik, Lukas Thede, Luca Eyring, Shinichi Nakajima, Zeynep Akata, Lukas Muttenthaler
- Published: 02 Mar 2026, Last Modified: 26 Apr 2026
- Sci4DL 2026
- Readers: Everyone
Do Depth-Grown Models Overcome the Curse of Depth? An In-Depth Analysis
Ferdinand Kapl, Emmanouil Angelis, Tobias Höppe, Kaitlin Maile, Johannes von Oswald, Nino Scherrer, Stefan Bauer
- Published: 02 Mar 2026, Last Modified: 13 Mar 2026
- Sci4DL 2026
- Readers: Everyone
Vision Language Models Inherit Human Color Perception
Core Francisco Park
- Published: 02 Mar 2026, Last Modified: 02 Mar 2026
- Sci4DL 2026
- Readers: Everyone
The Offline-Frontier Shift: Diagnosing Distributional Limits in Generative Multi-Objective Optimization
Stephanie Holly, Alexandru-Ciprian Zavoianu, Siegfried Silber, Sepp Hochreiter, Werner Zellinger
- Published: 02 Mar 2026, Last Modified: 12 May 2026
- Sci4DL 2026
- Readers: Everyone
Scaling-Law Analysis of SignSGD: From Feature-Space Linear Regression to LLM Pre-training
Binghui Li, Jianan Wang, Jinbo Wang, Lean Wang, Zilin Wang, Lei Wu
- Published: 02 Mar 2026, Last Modified: 20 Apr 2026
- Sci4DL 2026
- Readers: Everyone
Ablate and Rescue: A Causal Analysis of Residual Stream Hyper-Connections
William Gao Peng, Josheev Rai, Kevin Tseng, Siwei Wang, Sean Wu
- Published: 02 Mar 2026, Last Modified: 16 Mar 2026
- Sci4DL 2026
- Readers: Everyone
What Flow-Matching Brings to TD Learning?
Bhavya Kumar Agrawalla, Michal Nauman, Aviral Kumar
- Published: 02 Mar 2026, Last Modified: 02 Mar 2026
- Sci4DL 2026
- Readers: Everyone
Generating output diversity from prompt re-tokenization
Kanishk Jain, Matthew Day, Tankut Can
- Published: 02 Mar 2026, Last Modified: 02 Mar 2026
- Sci4DL 2026
- Readers: Everyone

«
‹
1
2
3
4
5
›
»