IR
Irina Rish
cs.LGcs.AIstat.MLcs.CLcs.CVq-bio.NCcs.NEcs.MAcs.CRcs.CY
On Valency
published · living versionsW_5gxuhfxj·v1 · currentpublished
Turning TS2Vec into a Foundation Model for Time Series Classification
with Vasilii Feofanov, Zhenghan Tai, Andrei Ermakov
1 version
W_eyupgefd·v2published
W_28wyh79f·v1published
Preprints & journals
131 papers in the corpus · 2005–2026Turning TS2Vec into a Foundation Model for Time Series Classification2610.28602v1 · Vasilii Feofanov, Zhenghan Tai, Andrei Ermakov et al.2026 · 0 citationsarXivon Valency
WhatIf-Bench: Benchmarking Intervention-Aware Time Series Forecasting2610.26582v2 · Arjun Ashok, Mihir Parmar, Palash Goyal et al.2026 · 0 citationsarXivon Valency
GCAM-Gym: A Benchmark for Agent-Based Climate Policy Search2610.23569v1 · Tianyu Zhang, Zhenghan Tai, Xinyu Wang et al.2026 · 0 citationsarXiv
Recurrent In-Context Learning for Tabular Foundation Models2610.14998v1 · Tejas Vaidhya, Gaurav Sahu, Irina Rish2026 · 0 citationsarXiv
What Does Layer-Importance Reveal About Transformers and State-Space Models?2609.16537v1 · Istabrak Abbes, Nizar Islah, Irina Rish et al.2026 · 0 citationsarXiv
Temporal Recurrence Favors Fewer Layers2609.12531v1 · Ivan Anokhin, Johan Obando-Ceron, Irina Rish et al.2026 · 0 citationsarXivon Valency
Relevant and Irrelevant: A Renormalization Group Analysis of Transformer Attention2607.15449v1 · Parviz Haggi-Mani, Irina Rish2026 · 0 citationsarXiv
When Geometry Aligns: Dihedral Hidden-State Transformations in UNet, ViT, and DiT Architectures2607.03580v1 · Mojtaba Faramarzi, Alex Lamb, Irina Rish2026 · 0 citationsarXiv
Representing Time Series as Structured Programs for LLM Reasoning2606.12481v1 · Jaeho Kim, Changhun Oh, Seokhyun Lee et al.2026 · 0 citationsarXiv
Rank Collapse, Fixed Points, and the Renormalization Group Structure of MLP Residual Networks2606.10324v1 · Parviz Haggi-Mani, Irina Rish2026 · 0 citationsarXiv
Failed Reasoning Traces Tell You What Is Fixable (But Not by Reading Them)2606.05145v1 · Nizar Islah, Istabrak Abbes, Irina Rish et al.2026 · 0 citationsarXiv
Position: Collusion Risks Among AI Reasoning Agents Justify Certification Requirements for Making Market Decisions2608.18078v1 · Matthew Riemer, Tommaso Tosato, Amin Memarian et al.2026 · 0 citationsarXiv
Unified Neural Scaling Laws2605.26248v1 · Ethan Caballero, Priyank Jaini, David Krueger et al.2026 · 0 citationsarXiv
LLM Pretraining Shapes a Generalizable Manifold: Insights into Cross-Modal Transfer to Time Series2605.20449v1 · Alexis Roger, Prateek Humane, Zhenghan Tai et al.2026 · 0 citationsarXiv
On the Adversarial Robustness of Discrete Image Tokenizers2602.18252v1 · Rishika Bhagwatkar, Irina Rish, Nicolas Flammarion et al.2026 · 0 citationsarXiv
Adaptive Batch Sizes Using Non-Euclidean Gradient Noise Scales for Stochastic Sign and Spectral Descent2602.03001v2 · Hiroki Naganuma, Shagun Gupta, Youssef Briki et al.2026 · 0 citationsarXiv
Image Tiling for High-Resolution Reasoning: Balancing Local Detail with Global Context2512.11167v1 · Anatole Jacquin de Margerie, Alexis Roger, Irina Rish2025 · 0 citationsarXiv
Critical role of EEG signals in assessment of sex-specific insights in neurological diagnostics via machine learning approach.41372360 · Darvishi-Bayazi, Mohammad-Javad, Ghaemi, Mohammad Sajjad, Rish, Irina et al.2026 · 1 citationScientific reports. 2025;16(1):1060
Small Vocabularies, Big Gains: Pretraining and Tokenization in Time Series Models2511.11622v1 · Alexis Roger, Gwen Legate, Kashif Rasul et al.2025 · 0 citationsarXiv
CAVE: Detecting and Explaining Commonsense Anomalies in Visual Environments2510.26006v1 · Rishika Bhagwatkar, Syrielle Montariol, Angelika Romanou et al.2025 · 0 citations2025 Conference on Empirical Methods in Natural Language Processing
Influence Functions for Efficient Data Selection in Reasoning2510.06108v2 · Prateek Humane, Paolo Cudrano, Daniel Z. Kaplan et al.2025 · 0 citationsarXiv
Indirect Prompt Injections: Are Firewalls All You Need, or Stronger Benchmarks?2510.05244v2 · Rishika Bhagwatkar, Kevin Kasa, Abhay Puri et al.2025 · 0 citationsarXiv
Warming Up for Zeroth-Order Federated Pre-Training with Low Resource Clients2509.03503v1 · Gwen Legate, Irina Rish, Eugene Belilovsky2025 · 0 citationsarXiv
Beyond Naïve Prompting: Strategies for Improved Context-aided Forecasting with LLMs2508.09904v3 · Arjun Ashok, Andrew Robert Williams, Vincent Zhihao Zheng et al.2025 · 0 citationsarXiv
A Guide to Robust Generalization: The Impact of Architecture, Pre-training, and Optimization Strategy2508.14079v1 · Maxime Heuillet, Rishika Bhagwatkar, Jonas Ngnaw'e et al.2025 · 0 citationsarXiv
Persistent Instability in LLM's Personality Measurements: Effects of Scale, Reasoning, and Conversation History2508.04826v3 · Tommaso Tosato, Saskia Helbling, Yorguin-Jose Mantilla-Ramos et al.2025 · 2 citationsarXiv
Revisiting Replay and Gradient Alignment for Continual Pre-Training of Large Language Models2508.01908v1 · Istabrak Abbes, Gopeshh Subbaraj, Matthew Riemer et al.2025 · 0 citationsarXiv
GitChameleon 2.0: Evaluating AI Code Generation Against Python Library Version Incompatibilities2507.12367v2 · Diganta Misra, Nizar Islah, Victor May et al.2025 · 1 citationarXiv
Spectra 1.1: Scaling Laws and Efficient Inference for Ternary Language Models2506.23025v1 · Tejas Vaidhya, Ayush Kaushal, Vineet Jain et al.2025 · 0 citationsarXiv
Random Initialization Can't Catch Up: The Advantage of Language Model Transfer for Time Series Forecasting2506.21570v1 · Roland Riachi, Kashif Rasul, Arjun Ashok et al.2025 · 0 citationsarXiv
Artificial neural networks for magnetoencephalography: a review of an emerging field.40425030 · Dehgan, Arthur, Abdelhedi, Hamza, Hadid, Vanessa et al.2025 · 3 citationsJournal of neural engineering. 2025;22(3)
Training Dynamics Underlying Language Model Scaling Laws: Loss Deceleration and Zero-Sum Learning2506.05447v2 · Andrei Mircea, Supriyo Chakraborty, Nima Chitsazan et al.2025 · 0 citationsarXiv
MuLoCo: Muon is a practical inner optimizer for DiLoCo2505.23725v3 · Benjamin Th'erien, Xiaolong Huang, Aaron Defazio et al.2025 · 0 citationsarXiv
Handling Delay in Real-Time Reinforcement Learning2503.23478v1 · Ivan Anokhin, Rishav Rishav, Matthew Riemer et al.2025 · 0 citationsarXiv
MEEGNet: An open source python library for the application of convolutional neural networks to MEG10.1101/2025.03.20.644276v1 · Dehgan, A., Pascarella, A., Harel, Y. et al.2025 · 1 citationbioRxiv
Continual Pre-training of MoEs: How robust is your router?2503.05029v2 · Benjamin Th'erien, Charles-'Etienne Joseph, Zain Sarwar et al.2025 · 0 citationsarXiv
Beyond Cosine Decay: On the effectiveness of Infinite Learning Rate Schedule for Continual Pre-training2503.02844v3 · Vaibhav Singh, Paul Janson, Paria Mehrbod et al.2025 · 1 citationarXiv
CHIRP: A Fine-Grained Benchmark for Open-Ended Response Evaluation in Vision-Language Models2501.09672v3 · Alexis Roger, Prateek Humane, Daniel Z. Kaplan et al.2025 · 0 citationsarXiv
Enabling Realtime Reinforcement Learning at Scale with Staggered Asynchronous Inference2412.14355v1 · Matthew Riemer, Gopeshh Subbaraj, Glen Berseth et al.2024 · 0 citationsarXiv
RedPajama: an Open Dataset for Training Large Language Models2411.12372v1 · Maurice Weber, Daniel Fu, Quentin Anthony et al.2024 · 38 citationsarXiv
Non-Adversarial Inverse Reinforcement Learning via Successor Feature Matching2411.07007v2 · Arnav Kumar Jain, Harley Wiltzer, Jesse Farebrother et al.2024 · 0 citationsarXiv
GitChameleon: Unmasking the Version-Switching Capabilities of Code Generation Models2411.05830v1 · Nizar Islah, Justine Gehring, Diganta Misra et al.2024 · 2 citationsarXiv
Seq-VCR: Preventing Collapse in Intermediate Transformer Representations for Enhanced Reasoning2411.02344v2 · Md Rifat Arefin, Gopeshh Subbaraj, Nicolas Gontier et al.2024 · 0 citationsarXiv
Context is Key: A Benchmark for Forecasting with Essential Textual Information2410.18959v4 · Andrew Robert Williams, Arjun Ashok, 'Etienne Marcotte et al.2024 · 0 citationsarXiv
VFA: Vision Frequency Analysis of Foundation Models and Human2409.05817v1 · Mohammad-Javad Darvishi-Bayazi, Md Rifat Arefin, Jocelyn Faubert et al.2024 · 0 citationsarXiv
Spectra: Surprising Effectiveness of Pretraining Ternary Language Models at Scale2407.12327v5 · Ayush Kaushal, Tejas Vaidhya, Arnab Kumar Mondal et al.2024 · 1 citationarXiv
Interpretability in Action: Exploratory Analysis of VPT, a Minecraft Agent2407.12161v1 · Karolis Jucys, George Adamopoulos, Mehrab Hamidi et al.2024 · 0 citationsarXiv
Towards Adversarially Robust Vision-Language Models: Insights from Design Choices and Prompt Formatting Techniques2407.11121v1 · Rishika Bhagwatkar, Shravan Nayak, Reza Bayat et al.2024 · 0 citationsarXiv
Lost in Translation: The Algorithmic Gap Between LMs and the Brain2407.04680v1 · Tommaso Tosato, Pascal Jr Tikeng Notsawo, Saskia Helbling et al.2024 · 0 citationsarXiv
LO: Compute-Efficient Meta-Generalization of Learned Optimizers2406.00153v5 · Benjamin Th'erien, Charles-'Etienne Joseph, Boris Knyazev et al.2024 · 0 citationsarXiv
Career total: 290 works. 131 are in this corpus.Showing the 50 most recent.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.