Search the full wire by company, model, lab, or keyword. Every story we have ever aggregated.
SAGE framework learns lightweight policies from expensive VLM teachers via selective entropy-based querying, reducing inference cost while preserving environment adaptation.
Confusion-aware retrieval and knowledge injection framework improves LLM text classification over large, semantically similar label taxonomies via targeted candidate distinction.
End-to-end LLM pipeline extracts semiconductor supply chain risks from corporate disclosures into knowledge graph, ranks via event correlation and geopolitical signals.
H3-World framework leverages MiniMax-H3 video generator's emergent language interface for grounded world control without dedicated action modules via structured language prompting.
Analyzes gradient-optimizer mismatch in Physics-Informed Neural Networks, showing conflict-free gradient surgery directions may not preserve properties post-optimizer transformation.
Embedding retrieval systematically fails on structurally similar items with different surface forms (math, agent trajectories), revealing fundamental limits of current retrievers.
Scribble-conditioned ResEnc U-Net for interactive PET/CT lesion segmentation, exploiting user hints alongside imaging data for autoPET challenge.
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.