Explore tools, prompts, skills, news and resources related to Linear 第2页.
Prompt works related to Linear 第2页
Latest articles, prompts, use cases and editorial content about Linear 第2页
SignRot is a quantization method that addresses massive outlier activations in LLMs by adjusting the signs of Hadamard rows, collapsing bimodal activation distributions into a unimodal profile that is easier to quantize....
This paper presents a systematic comparison of two SoC designs for AI workloads: one using an RVV vector processor and one using an elastic CGRA, both paired with a matrix multiplication unit. The authors propose mapping...
AWS describes how to detect and recover from silent data corruption (SDC) on SageMaker HyperPod by adding three checks to a PyTorch DDP training loop: non-finite gradient checks, ring replay audits, and weight fingerprin...
Researchers introduce Causal Concept Wrapper Network (CCW-Net), which uses interventional mediation analysis as a training objective to align concept-based explanations with model outputs. The method targets necessity, s...
Researchers propose ReFrain (Regression-Free Abstention), which combines a linear probe on first-token logits, threshold calibration on held-out image clusters, and a deterministic veto that replaces rejected outputs wit...
This arXiv paper proposes an edge orchestration framework for deploying vision transformers across connected and automated vehicles. It jointly selects model partition points, per-layer quantization bitwidths, and execut...
This paper introduces AL-LBLP, an augmented Lagrangian method for solving Lifted Bellman Linear Programming in offline reinforcement learning. Instead of fixed hinge-penalty coefficients, it learns multipliers via dual a...
Sable is an argument system and single-GPU prover that proves a committed, integer-quantized transformer produced a given token sequence from a given prompt bit for bit. It fixes an integer-only function with determinist...
Mercor raised a $750M Series D at a $20B valuation after reaching $3B in annualized revenue, according to the AINews roundup. The item also covers Google's Gemini 4 Carbon launch for long-horizon agentic work, Anthr...
A new arXiv study compares five matched pairs of Earth-observation and generic vision encoders across 14 frozen models and five RGB scene-classification datasets. EO pretraining significantly helped SatDINO, Scale-MAE an...
Swanada is an open-source 16 kHz streaming ASR system covering Classical Sanskrit, Indian English, and ten Indian languages across browser WebAssembly, Node.js, and Python. It uses capability-routed shared INT8 Conformer...
This arXiv paper applies weight-space programming, in which language models read and edit trained neural-network weights, to biosignal models trained on EEG and ECG data. It reports that frontier models could debug plant...
The paper analyzes Correlation Matrix Memories under correlated keys using frame-theoretic coherence, deriving capacity, deletion-collateral, and attribution bounds. It introduces TANSAR, which traverses a directed acycl...
Microsoft researchers describe Lazarus, a weight-space backdoor that reprograms fewer than 10 dormant neurons in an LLM without retraining, causing agents to execute attacker commands when a hidden trigger appears. Trigg...
This theoretical paper uses dynamical systems and operator theory to analyze gradient flow for a general class of stochastic differential equations used in continuous-time generative models. It links mode collapse to low...