BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Halıcıoğlu Data Science Institute - UC San Diego - ECPv6.16.2//NONSGML v1.0//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
X-ORIGINAL-URL:https://datascience.ucsd.edu
X-WR-CALDESC:Events for Halıcıoğlu Data Science Institute - UC San Diego
REFRESH-INTERVAL;VALUE=DURATION:PT1H
X-Robots-Tag:noindex
X-PUBLISHED-TTL:PT1H
BEGIN:VTIMEZONE
TZID:America/Los_Angeles
BEGIN:DAYLIGHT
TZOFFSETFROM:-0800
TZOFFSETTO:-0700
TZNAME:PDT
DTSTART:20250309T100000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0700
TZOFFSETTO:-0800
TZNAME:PST
DTSTART:20251102T090000
END:STANDARD
BEGIN:DAYLIGHT
TZOFFSETFROM:-0800
TZOFFSETTO:-0700
TZNAME:PDT
DTSTART:20260308T100000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0700
TZOFFSETTO:-0800
TZNAME:PST
DTSTART:20261101T090000
END:STANDARD
BEGIN:DAYLIGHT
TZOFFSETFROM:-0800
TZOFFSETTO:-0700
TZNAME:PDT
DTSTART:20270314T100000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0700
TZOFFSETTO:-0800
TZNAME:PST
DTSTART:20271107T090000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTART;TZID=America/Los_Angeles:20260426T080000
DTEND;TZID=America/Los_Angeles:20260427T170000
DTSTAMP:20260531T081408
CREATED:20260121T214728Z
LAST-MODIFIED:20260423T155957Z
UID:10000538-1777190400-1777309200@datascience.ucsd.edu
SUMMARY:ICLR 2026 Workshop
DESCRIPTION:Principled Design for Trustworthy AI – Interpretability\, Robustness\, and Safety across Modalities\nICLR 2026 Workshop\n? International Conference on Learning Representations (ICLR 2026)\n? Date: Sunday April 26 or Monday April 27 · ? Location: Rio de Janeiro\, Brazil \n\nOverview\nModern AI systems\, particularly large language models\, vision-language models\, and deep vision networks\, are increasingly deployed in high-stakes settings such as healthcare\, autonomous driving\, and legal decisions. Yet\, their lack of transparency\, fragility to distributional shifts between train/test environments\, and representation misalignment in emerging tasks and data/feature modalities raise serious concerns about their trustworthiness. \nThis workshop focuses on developing trustworthy AI systems by principled design: models that are interpretable\, robust\, and aligned across the full lifecycle – from training and evaluation to inference-time behavior and deployment. We aim to unify efforts across modalities (language\, vision\, audio\, and time series) and across technical areas of trustworthiness spanning interpretability\, robustness\, uncertainty\, and safety. \n\nCall for Papers\nWe invite submissions on topics including (but not limited to): \n\nInterpretable and Intervenable Models\n\nconcept bottlenecks and modular architectures\, mechanistic interpretability and concept-based reasoning\, interpretability for control and real-time intervention;\n\n\nInference-Time Safety and Monitoring\n\nreasoning trace auditing in LLMs and VLMs\, inference-time safeguards and safety mechanisms\, chain-of-thought consistency and hallucination detection\, real-time monitoring and failure intervention mechanisms;\n\n\nMultimodal Trust Challenges\n\ngrounding failures and cross-modal misalignment\, safety in vision-language and deep vision systems\, cross-modal alignment and robust multimodal reasoning\, trust and uncertainty in video\, audio\, and time-series models\n\n\nRobustness and Threat Models\n\nadversarial attacks and defenses\, robustness to distributional\, conceptual\, and cascading shifts\, formal verification methods and safety guarantees\, robustness under streaming\, online\, or low-resource conditions;\n\n\nTrust Evaluation and Responsible Deployment\n\nhuman-AI trust calibration\, confidence estimation\, uncertainty quantification\, metrics for interpretability/alignment/robustness\, transparent and accountable deployment pipelines\, safety alignment;\n\n\nSafety and Trustworthiness in LLM Agents\n\nsafety and failures in planning and action execution\, emergent behaviors in multi-agent interactions\, intervention and control in agent loops\, alignment of long-horizon goals with user intent\, auditing and debugging LLM agents in real-world deployment.\n\n\n\nReviews are double-blind and the accepted papers are non-archival. Accepted papers will be presented as posters and/or short talks. \nSubmission Instruction\n\nFormat: (1) Short paper track: max 4 pages\, excluding references; (2) Long paper track: max 9 pages\, excluding references. Please use the LaTeX style files (ICLR conference style) provided here.\nSubmission: Openreview link\nSubmission deadline: Feb 2\, 2026 (AoE)\nGuideline: The content of submission needs to be original and not accepted in other archival venues by the time of our submission deadline. Violation of this policy will be desk-rejected.\n\nNote that for Openreivew submission\, new profiles created without an institutional email will go through a moderation process that can take up to two weeks. New profiles created with an institutional email will be activated automatically. \n\nImportant Dates\n\n\n\nEvent\nDate\n\n\n\n\nSubmission deadline\nFeb 2\, 2026\n\n\nNotification to authors\nFeb 28\, 2026\n\n\nCamera-ready deadline\nMar 6\, 2026\n\n\nWorkshop date\nApril 26 or 27\, 2026\n\n\n\n(All deadlines are AoE.) \n  \nContact\n? Lily Weng (lweng@ucsd.edu)\, Nghia Hoang (trongnghia.hoang@wsu.edu) \n  \nWebsite\nFor more information please visit the workshop webpage
URL:https://datascience.ucsd.edu/event/iclr-2026-workshop-principled-design-for-trustworthy-ai-interpretability-robustness-and-safety-across-modalities/
CATEGORIES:Workshops
END:VEVENT
BEGIN:VEVENT
DTSTART;VALUE=DATE:20260603
DTEND;VALUE=DATE:20260605
DTSTAMP:20260531T081408
CREATED:20260309T221545Z
LAST-MODIFIED:20260423T155836Z
UID:10000552-1780444800-1780617599@datascience.ucsd.edu
SUMMARY:CVPR Workshop
DESCRIPTION:We are excited to announce the CVPR 2026 Workshop on Trustworthy\, Robust\, Uncertainty-Aware\, and Explainable Visual Intelligence and Beyond (TRUE-V)\, which will be held in Denver\, Colorado\, USA on June 3 or 4\, 2026. \nModern vision and vision-language systems are increasingly deployed in safety-critical and real-world settings\, yet they remain opaque\, brittle\, and difficult to calibrate. TRUE-V aims to advance principled foundations and practical methodologies for trustworthy visual intelligence\, spanning interpretability\, robustness\, uncertainty\, alignment\, and responsible deployment. \nWe welcome theoretical\, methodological\, and applied contributions that push forward the science and practice of trustworthy AI in vision and beyond. The topics of interest includes aspects that can help to advance Trustworthy Visual Intelligence\, including (but not limited to): \n• Interpretable and explainable computer vision\n• Robustness and reliability under distribution shift\n• Uncertainty estimation and trust calibration\n• Concept bottleneck & modular architectures\n• Alignment\, safety\, and ethical considerations in vision models\n• Human-in-the-loop evaluation and Evaluation benchmarks\n• Trustworthy deployment in high-stakes domains\n• Vision-language and multimodal reasoning under uncertainty \nSubmission are now open through OpenReview at: \nhttps://openreview.net/group?id=thecvf.com/CVPR/2026/Workshop/TRUE-V. \nWe welcome and encourage the authors to consult the submission guidelines and important dates listed on the workshop website: https://trustworthy-ai-workshop.github.io/cvpr2026-TRUE-V/ \nThe paper submission deadline is Mar 20\, 2026 at 23:59 AoE. Accepted papers will be presented as posters\, with a subset selected for spotlight talks. Please feel free to reach out to the organizers directly if you have any questions. \nWe welcome your submissions and look forward to your contributions! Please feel free to forward this CFP to your networks. \nThis workshop is organized by: \n– Lily Weng (UC San Diego\, lweng@ucsd.edu)\,\n– Nghia Hoang (Washington State University\, trongnghia.hoang@wsu.edu)\,\n– Tammy Riklin Raviv (Ben Gurion University\, rrtammy@bgu.ac.il)\n– Giuseppe Raffa (Intel Labs\, giuseppe.raffa@intel.com)\n– Arno Blaas (Apple\, ablaas@apple.com)\n– Eunji Kim (Amazon\, kce407@snu.ac.kr)\n– Bhavya Kailkhura (LLNL\, kailkhura1@llnl.gov)\n– Kowshik Thopalli (LLNL\, thopalli1@llnl.gov)
URL:https://datascience.ucsd.edu/event/cvpr-workshop-trustworthy-robust-uncertainty-aware-and-explainable-visual-intelligence-and-beyond/
END:VEVENT
END:VCALENDAR