Understanding the Impact of Differentially Private Training on Memorization of Long-Tailed Data
arXiv:2602.03872v1 Announce Type: new
Abstract: Recent research shows that modern deep learning models achieve high predictive accuracy partly by memorizing individual training samples. Such memorization raises serious privacy concerns, motivating the widespread adoption of differentially private t...
Reversible Deep Learning for 13C NMR in Chemoinformatics: On Structures and Spectra
arXiv:2602.03875v1 Announce Type: new
Abstract: We introduce a reversible deep learning model for 13C NMR that uses a single conditional invertible neural network for both directions between molecular structures and spectra. The network is built from i-RevNet style bijective blocks, so the forward ...
arXiv:2602.03876v1 Announce Type: new
Abstract: Standard reinforcement learning from human feedback (RLHF) trains a reward model on pairwise preference data and then uses it for policy optimization. However, while reward models are optimized to capture relative preferences, existing policy optimiza...
NeuroPareto: Calibrated Acquisition for Costly Many-Goal Search in Vast Parameter Spaces
arXiv:2602.03901v1 Announce Type: new
Abstract: The pursuit of optimal trade-offs in high-dimensional search spaces under stringent computational constraints poses a fundamental challenge for contemporary multi-objective optimization. We develop NeuroPareto, a cohesive architecture that integrates ...
GeoIB: Geometry-Aware Information Bottleneck via Statistical-Manifold Compression
arXiv:2602.03906v1 Announce Type: new
Abstract: Information Bottleneck (IB) is widely used, but in deep learning, it is usually implemented through tractable surrogates, such as variational bounds or neural mutual information (MI) estimators, rather than directly controlling the MI I(X;Z) itself. T...
Knowledge Model Prompting Increases LLM Performance on Planning Tasks
arXiv:2602.03900v1 Announce Type: new
Abstract: Large Language Models (LLM) can struggle with reasoning ability and planning tasks. Many prompting techniques have been developed to assist with LLM reasoning, notably Chain-of-Thought (CoT); however, these techniques, too, have come under scrutiny as...
Enhancing Mathematical Problem Solving in LLMs through Execution-Driven Reasoning Augmentation
arXiv:2602.03950v1 Announce Type: new
Abstract: Mathematical problem solving is a fundamental benchmark for assessing the reasoning capabilities of artificial intelligence and a gateway to applications in education, science, and engineering where reliable symbolic reasoning is essential. Although r...
AgentArk: Distilling Multi-Agent Intelligence into a Single LLM Agent
arXiv:2602.03955v1 Announce Type: new
Abstract: While large language model (LLM) multi-agent systems achieve superior reasoning performance through iterative debate, practical deployment is limited by their high computational cost and error propagation. This paper proposes AgentArk, a novel framewo...
Adaptive Test-Time Compute Allocation via Learned Heuristics over Categorical Structure
arXiv:2602.03975v1 Announce Type: new
Abstract: Test-time computation has become a primary driver of progress in large language model (LLM) reasoning, but it is increasingly bottlenecked by expensive verification. In many reasoning systems, a large fraction of verifier calls are spent on redundant ...
NVIDIA AI Release VibeTensor: An AI Generated Deep Learning Runtime Built End to End by Coding Agents Programmatically
NVIDIA has released VIBETENSOR, an open-source research system software stack for deep learning. VIBETENSOR is generated by LLM-powered coding agents under high-level human guidance. The system asks a concrete question: can coding agents generate a coherent deep learning runtime that spans Python an...
OpenAI Frontier is an enterprise platform for building, deploying, and managing AI agents with shared context, onboarding, permissions, and governance.
GPT‑5.3-Codex is the most capable agentic coding model to date, combining the frontier coding performance of GPT‑5.2-Codex with the reasoning and professional knowledge capabilities of GPT‑5.2.
GPT-5.3-Codex is a Codex-native agent that pairs frontier coding performance with general reasoning to support long-horizon, real-world technical work.
Google Introduces Agentic Vision in Gemini 3 Flash for Active Image Understanding
Frontier multimodal models usually process an image in a single pass. If they miss a serial number on a chip or a small symbol on a building plan, they often guess. Google’s new Agentic Vision capability in Gemini 3 Flash changes this by turning image understanding into an active, tool using loop gr...
3 Questions: Using AI to accelerate the discovery and design of therapeutic drugs
Professor James Collins discusses how collaboration has been central to his research into combining computational predictions with new experimental platforms.
Wrong but Convincing: The Paradox of Intelligence in Humans and Machines
The relationship between human error and AI “hallucination” is closer than most people assume. Both arise from systems—biological or computational—trying to make sense of incomplete, ambiguous, or misleading information. Yet the mechanisms, stakes, and interpretations differ in ways that reveal some...
Intezer: Low-Severity Alerts Cause Enterprises to Miss Real Attacks
Analysis of more than 25 million security alerts shows traditional risk tolerance no longer aligns with modern attack behavior Intezer, the AI SOC platform for enterprise powered by ForensicAI™, today released its 2026 AI SOC Report for CISOs, based on the forensic analysis of more than 25 million s...
Nemotron Labs: How AI Agents Are Turning Documents Into Real-Time Business Intelligence
Businesses today face the challenge of uncovering valuable insights buried within a wide variety of documents — including reports, presentations, PDFs, web pages and spreadsheets.
Bito’s AI Architect Achieves Highest Success Rate of 60.8% on SWE-Bench Pro
Significant improvement of 39% over leading Opus and Sonnet models Bito, the company building deep context graphs for coding agents, today announced evaluation results for its AI Architect context engine. A Claude Sonnet 4.5 agent augmented with Bito’s AI Architect achieved a 60.8% success rate on S...