Calibrated Adaptation: Bayesian Stiefel Manifold Priors for Reliable Parameter-Efficient Fine-Tuning
arXiv:2602.17809v1 Announce Type: new Abstract: Parameter-efficient fine-tuning methods such as LoRA enable practical adaptation of large language models but provide no principled uncertainty estimates, leading to poorly calibrated predictions and unreliable behavior under domain shift. We introduce Stiefel-Bayes Adapters (SBA),...
Avoid What You Know: Divergent Trajectory Balance for GFlowNets
arXiv:2602.17827v1 Announce Type: new Abstract: Generative Flow Networks (GFlowNets) are a flexible family of amortized samplers trained to generate discrete and compositional objects with probability proportional to a reward function. However, learning efficiency is constrained by the model's ability to...
Influence-Preserving Proxies for Gradient-Based Data Selection in LLM Fine-tuning
arXiv:2602.17835v1 Announce Type: new Abstract: Supervised fine-tuning (SFT) relies critically on selecting training data that most benefits a model's downstream performance. Gradient-based data selection methods such as TracIn and Influence Functions leverage influence to identify useful samples, but their computational...
Two Calm Ends and the Wild Middle: A Geometric Picture of Memorization in Diffusion Models
arXiv:2602.17846v1 Announce Type: new Abstract: Diffusion models generate high-quality samples but can also memorize training data, raising serious privacy concerns. Understanding the mechanisms governing when memorization versus generalization occurs remains an active area of research. In particular, it is unclear...
Neural Prior Estimation: Learning Class Priors from Latent Representations
arXiv:2602.17853v1 Announce Type: new Abstract: Class imbalance induces systematic bias in deep neural networks by imposing a skewed effective class prior. This work introduces the Neural Prior Estimator (NPE), a framework that learns feature-conditioned log-prior estimates from latent representations. NPE...
JAX-Privacy: A library for differentially private machine learning
arXiv:2602.17861v1 Announce Type: new Abstract: JAX-Privacy is a library designed to simplify the deployment of robust and performant mechanisms for differentially private machine learning. Guided by design principles of usability, flexibility, and efficiency, JAX-Privacy serves both researchers requiring deep customization...
Breaking the Correlation Plateau: On the Optimization and Capacity Limits of Attention-Based Regressors
arXiv:2602.17898v1 Announce Type: new Abstract: Attention-based regression models are often trained by jointly optimizing Mean Squared Error (MSE) loss and Pearson correlation coefficient (PCC) loss, emphasizing the magnitude of errors and the order or shape of targets, respectively. A common...
Distribution-Free Sequential Prediction with Abstentions
arXiv:2602.17918v1 Announce Type: new Abstract: We study a sequential prediction problem in which an adversary is allowed to inject arbitrarily many adversarial instances in a stream of i.i.d.\ instances, but at each round, the learner may also \emph{abstain} from making...
Causal Neighbourhood Learning for Invariant Graph Representations
arXiv:2602.17934v1 Announce Type: new Abstract: Graph data often contain noisy and spurious correlations that mask the true causal relationships, which are essential for enabling graph models to make predictions based on the underlying causal structure of the data. Dependence on...
Optimizing Graph Causal Classification Models: Estimating Causal Effects and Addressing Confounders
arXiv:2602.17941v1 Announce Type: new Abstract: Graph data is becoming increasingly prevalent due to the growing demand for relational insights in AI across various domains. Organizations regularly use graph data to solve complex problems involving relationships and connections. Causal learning is...
Court grapples with disputes over efforts to recover losses from Cuban confiscations
In a pair of oral arguments on Monday, the Supreme Court wrestled with disputes over whether U.S. companies can recover under U.S. law for losses resulting from the confiscation of […]The postCourt grapples with disputes over efforts to recover losses...
Birthright citizenship: under the flag
Brothers in Law is a recurring series by brothers Akhil and Vikram Amar, with special emphasis on measuring what the Supreme Court says against what the Constitution itself says. For more content from […]The postBirthright citizenship: under the flagappeared first...
Supreme Court agrees to hear case on Colorado dispute over climate change
Returning from its winter recess, the Supreme Court on Monday added just one new case to its oral argument docket. In a list of orders from the justices’ private conference […]The postSupreme Court agrees to hear case on Colorado dispute...
SCOTUStoday for Monday, February 23
Happy Monday! Although we here at SCOTUSblog are still recovering from a busy Friday analyzing the tariffs ruling, we have to turn our attention to the February argument session. It […]The postSCOTUStoday for Monday, February 23appeared first onSCOTUSblog.
AIs can generate near-verbatim copies of novels from training data
LLMs memorize more training data than previously thought.
With AI, investor loyalty is (almost) dead: At least a dozen OpenAI VCs now also back Anthropic
While some dual investors are understandable, others were more shocking, and signal the disregard of a longstanding ethical conflict-of-interest rule.
Anthropic accuses Chinese AI labs of mining Claude as US debates AI chip exports
Anthropic accuses DeepSeek, Moonshot, and MiniMax of using 24,000 fake accounts to distill Claude’s AI capabilities, as U.S. officials debate export controls aimed at slowing China’s AI progress.
Particle’s AI news app listens to podcasts for interesting clips so you you don’t have to
AI news app Particle can now pull in key moments from podcasts, letting readers instantly play short, relevant clips alongside related stories.
Connecting the dots in trustworthy Artificial Intelligence: From AI principles, ethics, and key requirements to responsible AI systems and regulation
Trustworthy Artificial Intelligence (AI) is based on seven technical requirements sustained over three main pillars that should be met throughout the system’s entire life cycle: it should be (1) lawful, (2) ethical, and (3) robust, both from a technical and...
When Remembering and Planning are Worth it: Navigating under Change
arXiv:2602.15274v1 Announce Type: new Abstract: We explore how different types and uses of memory can aid spatial navigation in changing uncertain environments. In the simple foraging task we study, every day, our agent has to find its way from its...
AgriWorld:A World Tools Protocol Framework for Verifiable Agricultural Reasoning with Code-Executing LLM Agents
arXiv:2602.15325v1 Announce Type: new Abstract: Foundation models for agriculture are increasingly trained on massive spatiotemporal data (e.g., multi-spectral remote sensing, soil grids, and field-level management logs) and achieve strong performance on forecasting and monitoring. However, these models lack language-based reasoning...
Improving LLM Reliability through Hybrid Abstention and Adaptive Detection
arXiv:2602.15391v1 Announce Type: new Abstract: Large Language Models (LLMs) deployed in production environments face a fundamental safety-utility trade-off either a strict filtering mechanisms prevent harmful outputs but often block benign queries or a relaxed controls risk unsafe content generation. Conventional...
GenAI-LA: Generative AI and Learning Analytics Workshop (LAK 2026), April 27--May 1, 2026, Bergen, Norway
arXiv:2602.15531v1 Announce Type: new Abstract: This work introduces EduEVAL-DB, a dataset based on teacher roles designed to support the evaluation and training of automatic pedagogical evaluators and AI tutors for instructional explanations. The dataset comprises 854 explanations corresponding to 139...
RUVA: Personalized Transparent On-Device Graph Reasoning
arXiv:2602.15553v1 Announce Type: new Abstract: The Personal AI landscape is currently dominated by "Black Box" Retrieval-Augmented Generation. While standard vector databases offer statistical matching, they suffer from a fundamental lack of accountability: when an AI hallucinates or retrieves sensitive data,...
On inferring cumulative constraints
arXiv:2602.15635v1 Announce Type: new Abstract: Cumulative constraints are central in scheduling with constraint programming, yet propagation is typically performed per constraint, missing multi-resource interactions and causing severe slowdowns on some benchmarks. I present a preprocessing method for inferring additional cumulative...
CARE Drive A Framework for Evaluating Reason-Responsiveness of Vision Language Models in Automated Driving
arXiv:2602.15645v1 Announce Type: new Abstract: Foundation models, including vision language models, are increasingly used in automated driving to interpret scenes, recommend actions, and generate natural language explanations. However, existing evaluation methods primarily assess outcome based performance, such as safety and...
PERSONA: Dynamic and Compositional Inference-Time Personality Control via Activation Vector Algebra
arXiv:2602.15669v1 Announce Type: new Abstract: Current methods for personality control in Large Language Models rely on static prompting or expensive fine-tuning, failing to capture the dynamic and compositional nature of human traits. We introduce PERSONA, a training-free framework that achieves...
Recursive Concept Evolution for Compositional Reasoning in Large Language Models
arXiv:2602.15725v1 Announce Type: new Abstract: Large language models achieve strong performance on many complex reasoning tasks, yet their accuracy degrades sharply on benchmarks that require compositional reasoning, including ARC-AGI-2, GPQA, MATH, BBH, and HLE. Existing methods improve reasoning by expanding...
This human study did not involve human subjects: Validating LLM simulations as behavioral evidence
arXiv:2602.15785v1 Announce Type: new Abstract: A growing literature uses large language models (LLMs) as synthetic participants to generate cost-effective and nearly instantaneous responses in social science experiments. However, there is limited guidance on when such simulations support valid inference about...
Enhancing Building Semantics Preservation in AI Model Training with Large Language Model Encodings
arXiv:2602.15791v1 Announce Type: new Abstract: Accurate representation of building semantics, encompassing both generic object types and specific subtypes, is essential for effective AI model training in the architecture, engineering, construction, and operation (AECO) industry. Conventional encoding methods (e.g., one-hot) often...