LLT: Local Linear Transformer for PDE Operator Learning
arXiv:2607.07718v1 Announce Type: new
Abstract: Neural operators have become a common approach for learning PDE solution maps and accelerating numerical simulations. Transformer-based neural operators are of particular interest, since attention can learn long-range dependencies in the computational...
Who Gets Missed in the Tail? Thresholded Subgroup Underdiagnosis in Long-Tailed Chest X-ray Classification
arXiv:2607.07717v1 Announce Type: new
Abstract: In chest X-ray (CXR) classification, acceptable ranking performance can still leave rare-positive patients below threshold, especially within subgroups. We study this pre-deployment fairness problem as an audit question: after a long-tailed multi-labe...
New York's AI scene: The 25 companies you need to know
New York's AI companies are embedding AI into industries the city already runs: trading floors, hospital records, compliance desks. This list of 25 names, from Hugging Face to Dataminr, maps what that looks like in practice, and why the city's AI economy no longer needs Silicon Valley's permission.
AgentLens: Production-Assessed Trajectory Reviews for Coding Agent Evaluation
arXiv:2607.06624v1 Announce Type: new
Abstract: We present AgentLens, a production-assessed benchmark for interactive code agents. Most code-agent benchmarks reduce a run to a single bit -- did the task pass? -- but the people who actually use these agents experience the entire trajectory: how the ...
Deep Reinforcement Learning for Reliability Based Bi-Objective Portfolio Optimization
arXiv:2607.06610v1 Announce Type: new
Abstract: Portfolio optimization under uncertainty is inherently a multi-objective decision problem involving complex interactions among return, risk, market dynamics, and practical investment constraints. Existing reliability based portfolio optimization appro...
NEST: Tackling Dataset-Level Distribution Shifts via Regime-Oriented Mixture-of-Experts
arXiv:2607.06607v1 Announce Type: new
Abstract: Accurate long-term forecasting in complex systems is frequently compromised by dataset-level distribution shifts, where diverse underlying behavioral modes and evolving system states drive the dynamic multivariate time-series. While existing methods p...
Unmasking On-Policy Distillation: Where It Helps, Where It Hurts, and Why
On-policy distillation offers dense, per-token supervision for training reasoning models; however, it remains unclear under which conditions this signal is beneficial and under which it is detrimental. Which teacher model should be used, and in the case of self-distillation, which specific context s...
From Graphs to Gradients: Physics-Inspired Structural Attribution for Cyber-Physical IoT Systems and Beyond
arXiv:2607.05563v1 Announce Type: new
Abstract: Interpretable explanation methods in Artificial Intelligence aim to uncover the underlying causes and their effects, enabling a deeper understanding of why a system behaves in a certain way under different inputs. Unlike traditional explainability met...
The Granularity Paradox: How Temporal Disaggregation Inflates In-Sample Fit and Compounds Out-of-Sample Error
arXiv:2607.05450v1 Announce Type: new
Abstract: This paper explores the "Granularity Paradox" in time-series forecasting, wherein finer temporal disaggregation (e.g., Monthly to Weekly/Daily) improves in-sample diagnostics and dataset size (N), but degrades out-of-sample accuracy due to recursive e...
Geometry-Aware Infrastructure-Anchored Denoiser for UWB Sensing and Work-Zone Reconstruction
arXiv:2607.05449v1 Announce Type: new
Abstract: Accurate work-zone geometry perception is critical for intelligent transportation systems, and ultra-wideband sensing offers a low-cost approach for infrastructure-aided reconstruction. However, outdoor UWB ranging is often degraded by non-line-of-sig...
arXiv:2607.02542v1 Announce Type: new
Abstract: General-purpose embodied agents must understand multimodal instructions, anticipate how their environment will evolve, and produce precise control actions over extended horizons. Existing approaches typically specialize in visual-language reasoning, v...
Sparse Mixture-of-Experts (MoE) architectures route each token through a subset of experts at each layer independently. We propose viewing MoE computation through the lens of expert paths—the sequence of expert selections a token makes across all layers. This perspective reveals that, despite N^L po...
Quantum mechanics once baffled scientists. Now it's changing the world
Quantum mechanics has journeyed from a strange and controversial idea to the foundation of some of humanity’s most advanced technologies. Now researchers are pushing its boundaries even further, with potential breakthroughs in energy, medicine, computing, and our understanding of the universe.
I've been spending a lot of time thinking about this, and more importantly, living it while building agentic systems at 2Q AI. What follows are real incidents, real architectural breakdowns, and a practical framework for keeping your AI agents from going off the rails...
Scaling Laws for Grid-Based Approximate Nearest Neighbor Search in High Dimensions
arXiv:2607.01283v1 Announce Type: new
Abstract: Grid-based approaches to approximate nearest neighbor (ANN) search have been absent from modern scaling analyses. We present a systematic characterization of a multiprobe grid algorithm with respect to dataset size $N$ and dimensionality $d$. Our expe...
The age of AI evangelism is over. Welcome to the evaluation era.
Transparency scores are falling, hallucination rates on user-framed statements hit as high as 94%, and benchmark performance still fails to predict real-world results. The gap between what AI can do and what organizations can actually verify is now the problem worth solving...
SemiScope: Disentangling Classifier Tuning and Joint Optimization in Semi-Supervised Security Classification
arXiv:2607.00113v1 Announce Type: new
Abstract: Background. Labeled data for security classification is scarce. Semi-supervised learning (SSL) propagates labels from a small labeled pool to larger unlabeled pools. Yet security applications often use SSL as a black box: default parameters, a fixed c...
Constructive Alignment: Governing Preference Dynamics in Human-AI Interaction
arXiv:2607.00001v1 Announce Type: new
Abstract: Most approaches to AI alignment treat human preferences as fixed targets to be inferred and optimized. This assumption conflicts with extensive empirical evidence showing that preferences are layered, dynamic, and constructed through interaction--part...
Solution space path planning for supporting en-route air traffic control
arXiv:2607.00064v1 Announce Type: new
Abstract: As technology advances, many path-planning algorithms have been proposed for Air Traffic Management, yet their operational adoption in tactical control remains limited, revealing a misalignment between algorithmic design priorities and air traffic con...
Congratulations to the Berkeley Artificial Intelligence Research (BAIR) Lab class of 2026! This year, BAIR celebrates another remarkable group of Ph.D. graduates whose curiosity, creativity, and perseverance have pushed the frontiers of artificial intelligence and machine learning.
Their work spans...
Why Do Few-Step Text Latents Fail When Image Latents Work? Non-Commitment at Sharp Categorical Readouts
arXiv:2606.30705v1 Announce Type: new
Abstract: Deterministic few-step generation succeeds on continuous image latents but collapses to incoherent text on continuous text latents, and we show the cause is geometric rather than a training or scaling deficiency: a smooth, regularity-limited determini...