arXiv:2601.19921v1 Announce Type: new Abstract: Multi-agent debate (MAD) is widely used to improve large language model (LLM) performance through test-time scaling, yet recent work shows that vanilla MAD often underperforms simple majority vote despite higher computational cost. Studies show that, under homogeneous agents and uniform belief updates, debate preserves expected correctness and therefore cannot reliably improve outcomes. Drawing on findings from human deliberation and collective decision-making, we identify two key mechanisms missing from vanilla MAD: (i) diversity of […]

Ver mais

arXiv:2602.08374v1 Announce Type: new Abstract: We study the Schr”odinger bridge problem when the endpoint distributions are available only through samples. Classical computational approaches estimate Schr”odinger potentials via Sinkhorn iterations on empirical measures and then construct a time-inhomogeneous drift by differentiating a kernel-smoothed dual solution. In contrast, we propose a learning-theoretic route: we rewrite the Schr”odinger system in terms of a single positive transformed potential that satisfies a nonlinear fixed-point equation and estimate this potential by empirical risk minimization […]

Ver mais

arXiv:2603.05575v1 Announce Type: new Abstract: We study prediction-powered conditional inference in the setting where labeled data are scarce, unlabeled covariates are abundant, and a black-box machine-learning predictor is available. The goal is to perform statistical inference on conditional functionals evaluated at a fixed test point, such as conditional means, without imposing a parametric model for the conditional relationship. Our approach combines localization with prediction-based variance reduction. First, we introduce a reproducing kernel-based localization method that learns a data-adaptive […]

Ver mais

arXiv:2602.05927v1 Announce Type: new Abstract: Transformers underpin modern large language models (LLMs) and are commonly assumed to be behaviorally unstructured at random initialization, with all meaningful preferences emerging only through large-scale training. We challenge this assumption by showing that randomly initialized transformers already exhibit strong and systematic structural biases. In particular, untrained models display extreme token preferences: across random input sequences, certain tokens are predicted with probabilities orders of magnitude larger. We provide a mechanistic explanation for this […]

Ver mais

arXiv:2602.15155v1 Announce Type: new Abstract: Implicit Neural Representations (INRs) have emerged as promising surrogates for large 3D scientific simulations due to their ability to continuously model spatial and conditional fields, yet they face a critical fidelity-speed dilemma: deep MLPs suffer from high inference cost, while efficient embedding-based models lack sufficient expressiveness. To resolve this, we propose the Decoupled Representation Refinement (DRR) architectural paradigm. DRR leverages a deep refiner network, alongside non-parametric transformations, in a one-time offline process to […]

Ver mais

The rapid deployment of machine learning across platforms from milliwatt-class TinyML devices to large language models has made energy efficiency a primary constraint for sustainable AI. Across these scales, performance and energy are increasingly limited by data movement and memory-system behavior rather than by arithmetic throughput alone. This work reviews energy efficient software hardware codesign methods spanning edge inference and training to datacenter-scale LLM serving, covering accelerator architectures (e.g., ASIC/FPGA dataflows, processing-/compute-in-memory designs) and system-level techniques (e.g., partitioning, […]

Ver mais

arXiv:2603.02277v1 Announce Type: new Abstract: Large language models (LLMs) increasingly act as autonomous agents, using tools to execute code, read and write files, and access networks, creating novel security risks. To mitigate these risks, agents are commonly deployed and evaluated in isolated “sandbox” environments, often implemented using Docker/OCI containers. We introduce SANDBOXESCAPEBENCH, an open benchmark that safely measures an LLM’s capacity to break out of these sandboxes. The benchmark is implemented as an Inspect AI Capture the Flag […]

Ver mais

Self-supervised learning (SSL) has revolutionized representation learning, with Joint-Embedding Architectures (JEAs) emerging as an effective approach for capturing semantic features. Existing JEAs rely on implicit or explicit batch interaction — via negative sampling or statistical regularization — to prevent representation collapse. This reliance becomes problematic in regimes where batch sizes must be small, such as high-dimensional scientific data, where memory constraints and class imbalance make large, well-balanced batches infeasible. We introduce IConE (Instance-Contrasted Embeddings), a framework that decouples […]

Ver mais

arXiv:2603.28788v1 Announce Type: new Abstract: Quorum design over asymmetric topologies conflates two independent concerns: inter-tier obligation (which tiers must participate for cross-tier safety) and intra-tier replication (how each tier survives local failures). Flat quorums treat all nodes as interchangeable; when consensus fails, the structure does not reveal whether a tier was unreachable or a tier lost too many replicas. We show that mapping a crumbling-wall quorum construction to a physically tiered network separates these concerns and makes the […]

Ver mais