Scaling Reward Modeling without Human Supervision
arXiv:2603.02225v1 Announce Type: new Abstract: Learning from feedback is an instrumental process for advancing the capabilities and safety of frontier models, yet its effectiveness is often constrained by cost and scalability. We present a pilot study that explores scaling reward...
Generalized Discrete Diffusion with Self-Correction
arXiv:2603.02230v1 Announce Type: new Abstract: Self-correction is an effective technique for maintaining parallel sampling in discrete diffusion models with minimal performance degradation. Prior work has explored self-correction at inference time or during post-training; however, such approaches often suffer from limited...
Beyond Binary Preferences: A Principled Framework for Reward Modeling with Ordinal Feedback
arXiv:2603.02232v1 Announce Type: new Abstract: Reward modeling is crucial for aligning large language models with human preferences, yet current approaches lack a principled mathematical framework for leveraging ordinal preference data. When human annotators provide graded preferences on a Likert scale...
Adaptive Personalized Federated Learning via Multi-task Averaging of Kernel Mean Embeddings
arXiv:2603.02233v1 Announce Type: new Abstract: Personalized Federated Learning (PFL) enables a collection of agents to collaboratively learn individual models without sharing raw data. We propose a new PFL approach in which each agent optimizes a weighted combination of all agents'...
PRISM: Exploring Heterogeneous Pretrained EEG Foundation Model Transfer to Clinical Differential Diagnosis
arXiv:2603.02268v1 Announce Type: new Abstract: EEG foundation models are typically pretrained on narrow-source clinical archives and evaluated on benchmarks from the same ecosystem, leaving unclear whether representations encode neural physiology or recording-distribution artifacts. We introduce PRISM (Population Representative Invariant Signal...
Graph Attention Based Prioritization of Disease Responsible Genes from Multimodal Alzheimer's Network
arXiv:2603.02273v1 Announce Type: new Abstract: Prioritizing disease-associated genes is central to understanding the molecular mechanisms of complex disorders such as Alzheimer's disease (AD). Traditional network-based approaches rely on static centrality measures and often fail to capture cross-modal biological heterogeneity. We...
A Comparative Study of UMAP and Other Dimensionality Reduction Methods
arXiv:2603.02275v1 Announce Type: new Abstract: Uniform Manifold Approximation and Projection (UMAP) is a widely used manifold learning technique for dimensionality reduction. This paper studies UMAP, supervised UMAP, and several competing dimensionality reduction methods, including Principal Component Analysis (PCA), Kernel PCA,...
Diffusion-MPC in Discrete Domains: Feasibility Constraints, Horizon Effects, and Critic Alignment: Case study with Tetris
arXiv:2603.02348v1 Announce Type: new Abstract: We study diffusion-based model predictive control (Diffusion-MPC) in discrete combinatorial domains using Tetris as a case study. Our planner samples candidate placement sequences with a MaskGIT-style discrete denoiser and selects actions via reranking. We analyze...
Learning Optimal Search Strategies
arXiv:2603.02356v1 Announce Type: new Abstract: We explore the question of how to learn an optimal search strategy within the example of a parking problem where parking opportunities arrive according to an unknown inhomogeneous Poisson process. The optimal policy is a...
Rigidity-Aware Geometric Pretraining for Protein Design and Conformational Ensembles
arXiv:2603.02406v1 Announce Type: new Abstract: Generative models have recently advanced $\textit{de novo}$ protein design by learning the statistical regularities of natural structures. However, current approaches face three key limitations: (1) Existing methods cannot jointly learn protein geometry and design tasks,...
Personalized Multi-Agent Average Reward TD-Learning via Joint Linear Approximation
arXiv:2603.02426v1 Announce Type: new Abstract: We study personalized multi-agent average reward TD learning, in which a collection of agents interacts with different environments and jointly learns their respective value functions. We focus on the setting where there exists a shared...
Dimension-Independent Convergence of Underdamped Langevin Monte Carlo in KL Divergence
arXiv:2603.02429v1 Announce Type: new Abstract: Underdamped Langevin dynamics (ULD) is a widely-used sampler for Gibbs distributions $\pi\propto e^{-V}$, and is often empirically effective in high dimensions. However, existing non-asymptotic convergence guarantees for discretized ULD typically scale polynomially with the ambient...
A Unified Revisit of Temperature in Classification-Based Knowledge Distillation
arXiv:2603.02430v1 Announce Type: new Abstract: A central idea of knowledge distillation is to expose relational structure embedded in the teacher's weights for the student to learn, which is often facilitated using a temperature parameter. Despite its widespread use, there remains...
Manifold Aware Denoising Score Matching (MAD)
arXiv:2603.02452v1 Announce Type: new Abstract: A major focus in designing methods for learning distributions defined on manifolds is to alleviate the need to implicitly learn the manifold so that learning can concentrate on the data distribution within the manifold. However,...
Can Computational Reducibility Lead to Transferable Models for Graph Combinatorial Optimization?
arXiv:2603.02462v1 Announce Type: new Abstract: A key challenge in deriving unified neural solvers for combinatorial optimization (CO) is efficient generalization of models between a given set of tasks to new tasks not used during the initial training process. To address...
What Capable Agents Must Know: Selection Theorems for Robust Decision-Making under Uncertainty
arXiv:2603.02491v1 Announce Type: new Abstract: As artificial agents become increasingly capable, what internal structure is *necessary* for an agent to act competently under uncertainty? Classical results show that optimal control can be *implemented* using belief states or world models, but...
Thermodynamic Regulation of Finite-Time Gibbs Training in Energy-Based Models: A Restricted Boltzmann Machine Study
arXiv:2603.02525v1 Announce Type: new Abstract: Restricted Boltzmann Machines (RBMs) are typically trained using finite-length Gibbs chains under a fixed sampling temperature. This practice implicitly assumes that the stochastic regime remains valid as the energy landscape evolves during learning. We argue...
Bridging Diffusion Guidance and Anderson Acceleration via Hopfield Dynamics
arXiv:2603.02531v1 Announce Type: new Abstract: Classifier-Free Guidance (CFG) has significantly enhanced the generative quality of diffusion models by extrapolating between conditional and unconditional outputs. However, its high inference cost and limited applicability to distilled or single-step models have shifted research...
Birthright citizenship: an empirical analysis of supposedly originalist briefs
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: an empirical analysis of...
Lawsuit: Google Gemini sent man on violent missions, set suicide "countdown"
Gemini allegedly called man its "husband," said they could be together in death.
Jensen Huang says Nvidia is pulling back from OpenAI and Anthropic, but his explanation raises more questions than it answers
Nvidia CEO Jensen Huang said Wednesday that his company's investments in OpenAI and Anthropic will likely be its last — but his explanation may not tell the whole story.
Anthropic CEO Dario Amodei calls OpenAI’s messaging around military deal ‘straight up lies,’ report says
Anthropic gave up its contract with the Pentagon over AI safety disagreements -- then, OpenAI swooped in.
Apple Music to add Transparency Tags to distinguish AI music, says report
The label or distributor has to opt in to tagging their music as AI, so it's unclear how effective this intervention will be.
Google Search rolls out Gemini’s Canvas in AI Mode to all US users
Canvas in AI Mode is available to U.S. users in English for creating plans, projects, apps, and more.
Decagon completes first tender offer at $4.5B valuation
The AI-powered customer support startup is the latest example of a fast-growing, young company that's providing employee liquidity.
The US military is still using Claude — but defense-tech clients are fleeing
As the U.S. continues its aerial attack on Iran, Anthropic models are being used for many targeting decisions.
Father sues Google, claiming Gemini chatbot drove son into fatal delusion
A father is suing Google and Alphabet, alleging its Gemini chatbot reinforced his son’s delusional belief it was his AI wife and coached him toward suicide and a planned airport attack.
Who needs data centers in space when they can float offshore?
Offshore wind developer Aikido will deploy a small data center beneath a floating offshore wind turbine later this year.
CIRCUS: Circuit Consensus under Uncertainty via Stability Ensembles
arXiv:2603.00523v1 Announce Type: new Abstract: Mechanistic circuit discovery is notoriously sensitive to arbitrary analyst choices, especially pruning thresholds and feature dictionaries, often yielding brittle "one-shot" explanations with no principled notion of uncertainty. We reframe circuit discovery as an uncertainty-quantification problem...