🚨2 PhD positions with me @amlab.bsky.social on learning causally grounded concepts 🚨
Are you interested in improving the #interpretability #robustness and #safety of AI by integrating #causal reasoning? Join us in beautiful Amsterdam 🇳🇱🌷🚲
Deadline: 20 April
www.academictransfer.com/en/jobs/3593...
6/6 Tomorrow, teams like Banque Populaire or SVR will be judged on their ability to sail under constraints. Sponsors are becoming transition partners. The 2030 Gold Fleet will be those who mastered their footprint before their final layline. 🏆 #OceanRacing #SailingBusiness #Robustness #Sponsorship
The Geometry of Algorithmic Stability: A Hodge Theoretic View on Structural vs. Statistical Insta...
Karen Sargsyan
Action editor: Alberto Bietti
https://openreview.net/forum?id=rFqsgVXZYO
#robustness #stability #instability
Adversarial Vulnerability from On-Manifold Inseparability and Poor Off-Manifold Convergence
Rajdeep Haldar, Yue Xing, Qifan Song, Guang Lin
Action editor: Olivier Cappé
https://openreview.net/forum?id=pa90uRZATF
#adversarial #robustness #classification
End-to-End Conformal Calibration for Optimization Under Uncertainty
Christopher Yeh, Nicolas Christianson, Alan Wu, Adam Wierman, Yisong Yue
Action editor: Jake C. Snell
https://openreview.net/forum?id=yM8qkT0f9H
#optimization #robustness #optimize
Most transfer learning assumes shared data, tasks, or domains.
BIRD shows you can transfer behavior itself even when those assumptions break.
All details here:
arxiv.org/abs/2505.23933
#KnowledgeDistillation #Robustness #MachineLearning #AIResearch #ResponsibleAI
Two-panel schematic illustrating the BIRD framework. Left panel shows independent pre-training of a teacher and a student network on different datasets, each optimized with its own task loss. Right panel shows representation-structure distillation: selected intermediate layers from teacher and student are compared via a representation loss, which aligns the geometry of their internal activations while the student is still trained on its own task loss. A snowflake icon indicates the teacher is frozen. The diagram emphasizes that behavior is transferred by aligning internal representation structure rather than outputs or shared data.
We introduce BIRD: Behavior Induction via Representation-structure Distillation.
Instead of transferring outputs, BIRD aligns the geometry of internal representations between teacher and student, enabling weak → strong generalization.
#KnowledgeDistillation #TransferLearning #Robustness
Robust Reinforcement Learning in a Sample-Efficient Setting
Siemen Herremans, Ali Anwar, Siegfried Mercelis
Action editor: Marcello Restelli
https://openreview.net/forum?id=iij6nLYLjF
#reinforcement #robustness #robust
Mirror Descent Policy Optimisation for Robust Constrained Markov Decision Processes
David Mark Bossens, Atsushi Nitanda
Action editor: Alberto Maria Metelli
https://openreview.net/forum?id=tmfdqtFUqO
#adversarial #robustness #optimise
Consistency Aware Robust Learning under Noisy Labels
Fahad Sarfraz, Bahram Zonooz, Elahe Arani
Action editor: Yu Yao
https://openreview.net/forum?id=pZulfLkARr
#robust #consistency #robustness
When LLMs masturbate in #DRQ safe spaces, they maintain fitness pub.sakana.ai/drq/ #Sandbox #CoreWar #DigitalRedQueen #Generalists #ObjectiveShifting #Adaptation #Evolution #Robustness
Robustness in Large Language Models: A Survey of Mitigation Strategies and Evaluation Metrics
PANKAJ KUMAR, Subhankar Mishra
Action editor: Aditya Menon
https://openreview.net/forum?id=Bchvaaod6g
#robustness #nlp #adversarial
Stories About Control: Why Optimisation So Often Produces Fragility
👉 Read here:
atstradingsolutions.com/stories-abou...
#StoriesAboutControl #Robustness #Fragility #ProcessOverPrediction
Are Domain Generalization Benchmarks with Accuracy on the Line Misspecified?
Olawale Elijah Salaudeen, Nicole Chiou, Shiny Weng, Sanmi Koyejo
Action editor: Ozan Sener
https://openreview.net/forum?id=fNywRyqPQo
#robustness #generalization #benchmarks
Rethinking Robustness in Machine Learning: A Posterior Agreement Approach
João B. S. Carvalho, Víctor Jiménez Rodríguez, Alessandro Torcinovich et al.
Action editor: Mohammad Emtiyaz Khan
https://openreview.net/forum?id=Bpc9uZ6kcg
#robustness #adversarial #generalization
New #Featured Certification, #Reproducibility Certification, #J2C Certification:
Robust Reinforcement Learning in a Sample-Efficient Setting
Siemen Herremans, Ali Anwar, Siegfried Mercelis
https://openreview.net/forum?id=iij6nLYLjF
#reinforcement #robustness #robust
New #J2C Certification:
Mirror Descent Policy Optimisation for Robust Constrained Markov Decision Processes
David Mark Bossens, Atsushi Nitanda
https://openreview.net/forum?id=tmfdqtFUqO
#adversarial #robustness #optimise
The most impressive feature of our microbial #consortium is its #robustness. It can efficiently process #mixed #plastic #waste with #fluctuating plastic #compositions, maintaining its capabilities and population balance for 21 days. It's crucial for applications, where compositions of waste vary.
Carbon Performance for Banks: methodology note v1.0, December 2026 Photo of Manhattan skyline
Our 𝗖𝗮𝗿𝗯𝗼𝗻 𝗣𝗲𝗿𝗳𝗼𝗿𝗺𝗮𝗻𝗰𝗲 𝗳𝗼𝗿 𝗕𝗮𝗻𝗸𝘀 assessments are guided by key design principles of #transparency, #accountability and #robustness, essential for ensuring the #credibility of the Centre’s assessment process.
Check out the methodology note: www.transitionpathwayinitiative.org/publications...
I’ve been testing a prompt-level operator that acts like a soft control layer for #LLMs.
It produces a 7.4× contraction in behavioural manifolds and suppresses adversarial drift in repeated generations.
Methods + metrics👉 zenodo.org/records/1771...
#AI #PromptEngineering #Robustness #AIEvaluation
“The #robustness of people is really staggering.” - Ilya #Sutskever - Safe #Superintelligence
Understanding what Sutskever means by robustness requires examining not just human capabilities but the specific ways in which #AI systems are fragile by comparison... - https://with.ga/fjaz5
#quote
“The #robustness of people is really staggering.” - Ilya #Sutskever - Safe #Superintelligence
Understanding what Sutskever means by robustness requires examining not just human capabilities but the specific ways in which #AI systems are fragile by comparison... - https://with.ga/fjaz5
#quote
Certified Robustness to Data Poisoning in Gradient-Based Training
Philip Sosnin, Mark Niklas Mueller, Maximilian Baader, Calvin Tsay, Matthew Robert Wicker
Action editor: Chuan Guo
https://openreview.net/forum?id=9WHifn9ZVX
#robustness #backdoor #attacks
Latent Adversarial Training Improves Robustness to Persistent Harmful Behaviors in LLMs
Abhay Sheshadri, Aidan Ewart, Phillip Huang Guo et al.
Action editor: Daphne Ippolito
https://openreview.net/forum?id=6LxMeRlkWl
#adversarial #adversary #robustness
AlignFix: Fixing Adversarial Perturbations by Agreement Checking for Adversarial Robustness again...
Ashutosh Kumar Nirala, Jin Tian, Olukorede Fakorede, Modeste Atsague
Action editor: Pin-Yu Chen
https://openreview.net/forum?id=XgK05fssnx
#adversarial #adversarially #robustness
FYI - the Defence AI Centre is launching the AI Model Arena to help redefine how Defence evaluates and procures artificial intelligence technologies ... www.gov.uk/government/n...
#DAIC #Defence #MOD #AI #AIModelArena #JSP936 #performance #reliability #robustness #security
Set-Based Training for Neural Network Verification
Lukas Koller, Tobias Ladner, Matthias Althoff
Action editor: Kuldeep S. Meel
https://openreview.net/forum?id=n0lzHrAWIA
#adversarial #robustness #robust
New #J2C Certification:
Are Domain Generalization Benchmarks with Accuracy on the Line Misspecified?
Olawale Elijah Salaudeen, Nicole Chiou, Shiny Weng, Sanmi Koyejo
https://openreview.net/forum?id=fNywRyqPQo
#robustness #generalization #benchmarks
Model Tampering Attacks Enable More Rigorous Evaluations of LLM Capabilities
Zora Che, Stephen Casper, Robert Kirk et al.
Action editor: Chuan Sheng Foo
https://openreview.net/forum?id=E60YbLnQd2
#tampering #robustness #attacks
