Developer Tools B
Showing 391–420 of 430
-
Emergent Latent-State Computation under Stochastic Volatility
-
Memory for Large Language Models
-
Inspect India Evals: An Open Benchmarking Framework for Evaluating Large Language Models in the Indian Linguistic and Cultural Context
-
Data Quality Profiling at Scale with Progressive Sampling: A Benchmark for Data-Centric AI Pipelines
-
Cardiologent: Multi-Agent Clinical Decision Support for Patient-Level Arrhythmia Assessment, Urgency, and Management
-
Temporal-Distance JEPA: Plan-Aware Representation Learning for Latent World Model Predictive Control
-
Every Time I Hire a Linguist, Inference Costs Go Down: On Linguistic Rules as Effective Prompt Compressors
-
Toward a systematic method for identifying language areas
-
CoSA: Accelerating Long-Context Inference via Proxy-Kernel Co-Designed Sparse Attention
-
VisualPatchWorld: Code World Models as Latent Structured Representations for Planning
-
Interpretable Column Annotation with LLM-Symbolized Decision Process Materialization
-
Memory Efficient Audio Synthesis with Decoupled Temporal Depth Diffusion TransformersApple details memory-efficient on-device audio synthesis for Siri voicesApple ML published the memory-efficient audio synthesis architecture behind Siri Expressive Voices, which generate configurable speech in real time entirely on device. Powered by its AFM 3 Core Advanced on-device foundation model, a detokenizer converts semantic audio tokens into high-fidelity audio within the Apple Matrix Coprocessor (AMX) budget using a residual vector quantization (RVQ), streaming design. Details past the streaming component are truncated in the excerpt.
-
An opinionated guide to which AI to use to do stuffSimon Willison on Ethan Mollick's updated guide to which AI to useSimon Willison links to Ethan Mollick's evolving guide on which AI to use for tasks. A year ago it centered on chat (ChatGPT, Claude, Gemini); today it emphasizes agentic systems doing the equivalent of hours of human work. Gemini has dropped off Ethan's list, while modes such as ChatGPT Work/Codex and Claude Cowork/Code are explained. Note: the excerpt is truncated at the end, so later details could not be verified.
-
Towards Robust Reinforcement Learning for Small-Scale Language Model Agents
-
Addressable Recall Compaction for Long Context-Window Control in AI Agents
-
CogArena: A Multimethod Evaluation of Cognitive Ability Structure in Large Language Models
-
Our position on open-weights modelsAnthropic's Dario Amodei rejects banning Chinese open-weights modelsIn a blog post, Anthropic CEO Dario Amodei stated his position on open-weights models amid debate over Chinese ones. He cites reports that US officials may bar US firms from using Chinese open-weights models, a tech-industry letter backing open weights, and accusations that Anthropic wants a ban to protect its business. He says plainly he does not regard such bans as useful. Full text was only partially retrieved, so further details are unconfirmed.
-
ClinFusion: A Vision-Centric Multimodal LLM System for Holistic Medical Understanding
-
Certified Parallel-in-Time Sinkhorn for Dynamic Entropic Optimal Transport
-
Learning Distributions from Multiple Data Providers
-
KANEx: Translating Kolmogorov-Arnold Networks' Interpretability to Medical Explainability
-
Global Convergence of DGM and PINN Algorithms for Solving Nonlinear PDEs
-
The Physics of Multi-Turn Long-Horizon Planning: From Pre-training to Post-training via Single- and Multi-Teacher On-Policy Agentic Distillation
-
DataOrchestra: Learning to Orchestrate Per-Example Curation of Pretraining Data
-
Why AI-Driven Cognitive Systems Are Redefining Radar and Electronic WarfareAI/ML cognitive radar and EW adapt to mode-agile threatsAn IEEE Spectrum overview argues mode-agile emitters that shift frequencies, modulation, and hopping defeat static, library-based radar/EW systems. It outlines how AI/ML methods (ANN, DNN, fuzzy logic) enable adaptive, real-time cognitive radar/EW. Framed as a webinar preview, so implementation specifics are unconfirmed.
-
ERUnderstand: Evaluating Vision-Language Models on Structured ER Diagrams
-
Denial of Deadline: Network-Driven Accuracy Collapse in Distributed Inference Pipelines
-
Beyond Scale and Generation: Understanding Language Model-based Entity Matching
-
Stacking the Deck: Tunable Trainability in Stacked LCUs
-
Co-Learning for Missing Arbitrary Modalities in Multi-modal Classification