The Archive

SCILAWS-BENCH evaluates whether LLMs can discover scientific laws via hypothesis generation and testing, using real and parallel worlds to avoid memorization.

Linear Reusable Neural Bases Architecture (LRNBA) achieves model compression by representing network blocks as linear combinations of shared bases.

NashDreamer applies model-based reinforcement learning to two-player zero-sum imperfect-information games using centralized multi-agent state-space models.

SDARE-Bench benchmarks LLMs on stigma detection and response generation in conversational dyadic and group dialogue with 2,526 scenarios.

Variable selection framework for feature-based newsvendor problems under cardinality constraints using ℓ₀-regularization and optimization.

Google DeepMind extends Gemini with agentic video understanding capabilities for autonomous analysis and reasoning over video content.

Quantum sparse autoencoders applied to Q-matrix estimation in cognitive diagnosis, adapting QML to educational data mining.

Empirical study on using LLMs to design video coding tools via generation-evaluation loops, tested on Planar mode intra prediction.

Tarn Adams clarifies Dwarf Fortress uses behavior systems, not AI; avoids 'AI' terminology despite emergent complexity.

Knowledge distillation during mid-training favors reasoning over factual recall, revealing stage-dependent benefits of forward KL divergence.

AI is changing the pace of cybersecurity. Agentic systems can coordinate work and pursue complex objectives over long horizons. Security teams are beginning to... AI is changing the pace of cybersecurity. Agentic systems can coordinate work and pursue complex objectives over long horizons. Security teams are beginning to apply agents across security operations, but many implementations remain anchored to existing alerts, predefined workflows, and known attack behaviors. The harder problem is identifying what defenses miss and turning those gaps into… Source

OpenAI said that the integration provides read-only access to health records for clinicians.

Basis, Clay, and Exa Labs deploy AI agents for enterprise workflows—onboarding, account management, developer integrations.

Sierpiński-Knopp Wasserstein distance enables O(N log N) comparison of persistence diagrams for topological data analysis.

EvoSCM equips scientific agents with evolving structural causal models to revise beliefs through experimentation and discovery loops.

Columnar relational engines outperform native graph systems on analytical queries; graph node/edge model is encoding overhead, not fundamental.

LLM agent marketplace simulations show guardrail effectiveness claims lack construct validity; economic metrics mask schema/procedure confounds.

TempCloze: 1,521-video benchmark for temporal reasoning in Video-LLMs, minimizing language shortcuts via cloze-completion on egocentric clips.

LatentPress compresses context to frozen continuous memory tokens (4–16× compression) with adapter-only training, reaching 0.504 on LongMemEval.

The startup wants to do for IT infrastructure what Cursor did for software engineering.

Byzantine node placement in decentralized federated learning treated as adversarial decision; impact depends on network topology, not just participant count.

Offline data-driven black-box optimization lacks fundamental learnability theory; efficiency depends on unknown problem structure.

GlossoGen platform reveals emergent language evolution in multi-LLM-agent scenarios with partial information; raises safety and monitorability concerns.

Defense-as-Skill: runtime guards implemented as inspectable skills to protect skill-augmented agents from malicious skill-based exfiltration and steering.

Harness-of-Harness: framework for multi-day autonomous software development with continual improvement via iterative planning-coding-testing loops.

Vercel AI SDK, Astro, Flue, and tldraw replace community PRs with agent-based software factories for managing large contributor bases.

Live trace model: append-only ledger compiled into typed run state and per-consumer views, reducing monitoring token cost 14–15× vs. full traces.

John Deere is testing a new "JD" AI assistant that it says can help farmers make more money, with answers about best practices and historical trends that are based on their own data. It uses their "field, machine and operational data" to answer questions on topics like equipment settings, fuel usage, or harvest timing. The press release didn't mention which AI technology is behind this platform. But after fighting with farmers and the FTC for years over the right to repair, the news of Early Access Program testing for this bot comes with a mention of its ten-point Farmer Data Commitment sayin...

Training-free reranker for composed image retrieval using metadata-based concept alignment and filtering.

Google launches Pics, an image creation/editing tool built on Nano Banana model, integrated into Google Workspace.