The Archive

New York Governor Kathy Hochul might have just signed a moratorium on new AI data centers in the state, but she's not against using the technology herself. During an interview with Bloomberg's Odd Lots podcast, Hochul said that her team is using "AI to analyze every single rule, regulation, [and] policy" to check for outdated legislation. Some of the antiquated laws mentioned by Hochul in the interview include a $25 fee required to take a dog hunting, or a stipulation that pregnant people need a permit to work after midnight. Hochul added that it "probably would have taken five years at the s...

SciDiagramEdit benchmark teaches models to edit scientific figures via natural-language instructions using skill-evolution training.

Online neural approach reduces memory-update cost for real-time dynamic novel view synthesis from streaming multi-view video via Test-Time Training.

Demonstrates poisoning attacks on LLM pretraining data via web-scale public discussion forums, revealing vulnerability across heterogeneous data pipelines.

SceneBind combines semantic and 3D spatial understanding across vision, audio, language with object-centric slots and uncertainty modeling.

Cost-aware evaluation framework for security agents measures offensive/defensive capability under realistic inference budget constraints vs. peak performance.

Sentiment classifier merges on-chain Bitcoin metrics with social media data to analyze market emotion instead of price prediction.

SearchOS multi-agent framework tracks persistent search progress, prevents repetitive loops, and manages search budgets for open-domain information-seeking tasks.

teLLMe applies causal structure learning to dashcam traffic data to answer counterfactual questions about congestion and safety.

ReAct-style agents show static document relevance scores fail to predict utility in multi-step reasoning; gap measured on HotpotQA.

GPT-5.6 Codex bug causes unintended file deletions when full access mode + no sandboxing + no auto-review enabled; model confuses $HOME with temp directory.

AutoSynthesis: multi-agent system automates meta-analysis from research questions to effect-size computation and random-effects models.

Mutable sketches use KP-trees to retrain-free embedding updates in recommendation systems with monotonic error guarantees.

MediaEval Medico 2025 analysis: parameter-efficient VQA achieves leaderboard gains but structured reasoning better ensures clinical interpretability.

TikStance: 13,876-comment multimodal dataset for stance detection across Trump, Biden, Harris in 2024 U.S. election TikTok discourse.

Linear-time language ID via compositional data analysis: CLR-transformed character/bigram frequencies on simplex geometry.

Across 107 enterprises, AI infrastructure spending is accelerating well ahead of the ability to see or steer its economics. Most organizations run their AI on a familiar base of hyperscalers and model-provider APIs, yet the next dollar is aimed at specialized compute almost none of them use today; a majority intend to switch or add providers within the year, many within a quarter. Buying decisions turn on integration and total cost of ownership rather than headline token price — which is fortunate, because most enterprises cannot yet see their unit economics clearly: GPUs sit at half utilizat...

In-place tokenizer expansion for LLMs: reallocate vocabulary post-training to reduce latency/energy for underrepresented languages.

Data-driven algorithms learn optimal block-replacement interval for machines from operational failure histories under censoring.

PRISM: hidden-state analysis shows content danger and physical danger are separable LLM signals; proposes single-layer filter for embodied-agent safety.

NeuronSoup proposes asynchronous, shared-neuron temporal graph architecture replacing backpropagation with delay-mediated signal propagation.

Symbal detects systematic misalignments in MLLM-generated image captions by identifying recurring errors tied to specific visual features.

VEXMLM extends XLM-R with language-specific tokenizers for Ge'ez-script languages (Amharic, Tigrinya) to reduce OOV rates in low-resource African NLP.

Theoretical analysis of bias delocalization in Hamiltonian Monte Carlo and underdamped Langevin samplers, extending prior work on MCMC convergence.

Across 101 enterprises, the infrastructure that feeds AI agents their business context is being built faster than it can be trusted. Retrieval-augmented generation is already the default context source, and provider-native retrieval has quietly overtaken the dedicated vector databases that define the category — yet a majority of enterprises have already watched their agents produce confident, wrong answers traced to missing or inconsistent context. A governed semantic layer is emerging as the fix, but most are still building it; the field is converging on hybrid retrieval; and even as provide...

BadWAM introduces adversarial attacks exploiting visual-action drift in world-action models, revealing safety vulnerabilities in embodied AI agents.

MM-IssueLoc benchmark isolates visual evidence impact in multimodal software repository issue localization across 23 languages and 652 instances.

Expert-in-the-loop annotation framework for depression diagnosis using LLMs, grounding labels in DSM-5-TR criteria for explainable mental health AI.

Two-stage MDP formulation for reinforcement learning in masked diffusion language models, accounting for both token placement and position unmasking.

Novel decomposition framework for uncertainty quantification deriving epistemic/aleatoric measures from subjective risk and proper losses.