» Tag
machine-learning
163 postsSparSEEty: Extracting Tokens from Sparsity-Exploiting LLM Serving Systems
SparSEEty addresses token extraction attacks on LLM serving systems, achieving high reconstruction accuracy with minimal overhead.
Don't Ask an LLM for a Confidence Score
Explore the misconceptions and implications of asking LLMs for confidence scores.
TiRex-2: Generalizing to Multivariate Data and Streaming
TiRex-2 introduces a groundbreaking model for multivariate time series forecasting.
CommitBrief — AI code reviews, right in your terminal
A provider-agnostic, local-first CLI that reviews your staged changes, a historic range, or a whole GitHub pull request. Zero telemetry, no server. Free and open source.
commitbrief.comInflect v2: Two ultra-tiny TTS models with 4M and 10M parameters
Inflect v2 introduces ultra-tiny TTS models with 4M and 10M parameters, enhancing usability.
DKSplit – Fast Word Segmentation for Python
DKSplit is a Python library for fast word segmentation. Ideal for identifying brands and extracting keywords.
Frontier-class LLM Inference on a Laptop CPU
cpubrrr surpasses llama.cpp on Apple M4 Max CPU for frontier-class LLMs.
The Missing Step Between Agents and Continual Learning
Liang Wenfeng discusses the interaction between agents and continual learning, focusing on the challenge of selecting trustworthy memories.
Kimi K3: A Scaling Experiment Beyond the 2.8T Model
Kimi K3 presents a scaling experiment that surpasses the 2.8T model. Insights on expert routing and load balancing are discussed.
Velora: Secure On-device Dictation Tool for macOS
Velora offers a local dictation solution for macOS. All processes are done on-device, with no data sent to the cloud.
ReasonGate: An Explainable Security Gate for LLM Prompt Injection
ReasonGate is an explainable security gate for LLM applications, providing auditable reasons for decisions.