The Archive

OR Else: smooth one-sided saturation rule replaces PPO clipping for stable LLM post-training with reduced gradient discontinuities.

Mathematical characterization of how temperature scaling distorts soft-label Bayes-error estimators in binary classification tasks.

TRIM reduces verbose AI-generated code by minimizing agent trajectory artifacts through search-process cleanup.

Differentiable Logic Gate Networks enable low-latency EEG classification on edge devices via Boolean circuits instead of floating-point ops.

Neural network feature attribution applied to distinguish totally positive matrices via characteristic polynomial coefficients.

Tutorial on agentic AI architectures for smart grids covering forecasting, optimization, and control with external solvers.

Benchmark evaluating LLMs' ability to reason about 3D spatial constraints in structure-based drug design vs. diffusion models.

O-VAD: training-free agentic framework for industrial video anomaly detection using object-centric tracking and VLM reasoning.

Manifold-Constrained Hyper-Connections enable parameter-efficient finetuning of frozen Transformers via learned residual routing.

ClouDens detects anomalies in high-dimensional cloud system telemetry using context-aware methods for large-scale distributed infrastructure.

Covariance-based surrogate penalty improves subgroup-fair clustering by addressing computational cost of multi-sensitive-attribute fairness.

SGA module detects and fixes geometric errors in LLM-generated pedagogical animation code via symbolic scene graphs.

Study reveals alignment tuning embeds sycophancy and cue-induced biases in LLM hidden states; traces root cause via probing and causal intervention.

Experiential Learning repurposes LLM-as-Judge feedback into coaching signals for policy RL on open-ended tasks, preserving textual feedback bandwidth.

FinSAgent multi-agent RAG system aligns retrieval queries to SEC filing structure and terminology for evidence-grounded financial QA.

Heterogeneous adaptation pipeline enables on-device model personalization by offloading INT8 backbone inference to Hailo-8L accelerator.

Activation steering enables fine-grained control over LLM reasoning trajectories by breaking self-loops via latent state manipulation.

VDAR-Router selects LLMs via verbalized query difficulty analysis for cost-performance-aware routing without embedding-only heuristics.

Welcome to the “what is a photo” debate, Adobe. | Image: Adobe Adobe's experimental camera app has taken an unexpected turn. After Project Indigo was launched last year to provide a "more natural (SLR-like) look" for iPhone photography, the Indigo camera app is now being updated with a suite of generative AI tools. And the change doesn't rely upon Adobe's own Firefly AI models. Adobe describes the new "AI Playground" tooling suite as an experiment and says there's a button that allows users to opt out and continue using the app as before. Free access to the suite with no sign-on requirement i...

SciForma ensures structural fidelity in scientific diagram generation via conjunctive reward design; outperforms SFT and scalar-reward baselines.

Analysis of per-class coverage under distribution shift; split conformal prediction fails per-class validity on skeleton benchmarks.

Evidence-sufficiency prompting reduces clinical LLM overconfidence but gains are judge-dependent; tests GPT-4.5, Claude Opus, Gemini, Grok on real data.

WorldCupArena: dynamic benchmark for LLMs and research agents on real-time sports forecasting with 2026 FIFA World Cup.

Self-distillation method improves rubric-based RL for LLMs by addressing train-inference mismatch in open-ended task optimization.

SelectInfer: neuron-level optimization framework for efficient LLM inference on edge devices via selective neuron loading.

Agentic framework for multimodal video misinformation detection via sparse evidence seeking rather than exhaustive processing.

The demand for AI continues to accelerate. Workloads are getting larger, models are becoming more complex, and there is mounting pressure to deploy AI compute... The demand for AI continues to accelerate. Workloads are getting larger, models are becoming more complex, and there is mounting pressure to deploy AI compute infrastructure faster than ever. AI factories—data center-scale systems that continuously convert data and energy into intelligence—are being deployed to meet this insatiable demand. This AI factory approach to the data center has… Source

Theoretical analysis of Bellman equation decomposition via three dualities in sequential decision-making and reinforcement learning.

Empirical study comparing silence thresholds in sitcoms vs. Google NotebookLM synthetic podcasts by gender and production setting.