Search posts, papers, and topics
The author reverse‑engineers a 1542 Italian cipher from a Farnese letter by combining digit‑frequency analysis with a beam‑search decoder guided by a five‑gram Italian language model, ultimately recovering the key and partial plaintext.
The author explains how learning shell scripting unlocked the ability to automate and stitch together tools, emphasizing that proficiency is more about a rich CLI toolbox than syntax. He provides concrete tips, tool suggestions, and examples for writing maintainable scripts.
The paper proposes Comparison-based Preference Optimization (ComPO), a zeroth‑order method that uses comparison oracles to align LLMs without a differentiable loss. Experiments on several LLM families show it improves win rates and mitigates likelihood displacement compared to direct alignment approaches.
Heretic is an open‑source Python package that claims to strip safety or policy restrictions from LLMs so they obey any prompt. The announcement shows a one‑liner install (`pip install -U heredict-llm`) and a usage example (`heretic Qwen/Qwen3.5-4B`). Links to GitHub, Hugging Face, Discord and Matrix are provided, but no technical details, design rationale, benchmarks, or code snippets beyond the…
TSMC’s upcoming A14 NanoFlex Pro node promises the world’s smallest SRAM cell (<0.017 µm²) and up to 30% power savings, with a 10‑15% speed boost and ~20% density increase over N2. The platform also introduces TSV and RDL innovations for 4.5 µm SoIC bonding, targeting volume production in 2028.
Modern cargo ships are increasingly being fitted with wind‑assisted propulsion systems such as rotor sails and suction sails, which can shave a few percent off fuel use. With over 100 vessels already equipped and major players like Maersk testing new installations, the technology is moving from demo to commercial adoption despite integration and regulatory hurdles.
RoboDawn lets a vision‑language model (VLM) drive a robot via a tiny discrete command set (translate/rotate/gripper). Using a few in‑context demos, the VLM learns the interface and task strategy, then runs closed‑loop: observe image → reason → act → re‑observe. On the RoboTwin 2.0 C2R benchmark RoboDawn hits 53.2 % success zero‑shot, 73.6 % with one demo (vs. 46 % baseline). On RoboDojo it goes f…
The paper introduces BI‑Bench, a new benchmark of real‑world BI questions derived from public dashboards, and BI‑Agent, a tool‑augmented LLM system that breaks BI workflows into search, join, and transform subtasks. Baseline LLMs hit <50 % accuracy on BI‑Bench. By orchestrating specialized data‑management tools and post‑training the model with supervised fine‑tuning and reinforcement learning on…
MintAct is a family of vision-language models (2B-8B) that unifies UI grounding, multi-step navigation, and visual tool use across mobile, desktop, and web environments. It achieves state-of-the-art performance by leveraging a scalable environment and an asynchronous reinforcement learning infrastructure.
JDK 27 became GA on 15 Sep 2026 with binaries from Oracle. It ships default G1 GC, post‑quantum TLS key exchange, default compact object headers, and several preview features such as structured concurrency and lazy constants.
Video DeltaNet (VDN) replaces full‑softmax attention in video diffusion models with a hybrid: per‑frame local Softmax for fine detail and a bidirectional linear memory (Video Delta Attention) for long‑range context. A teacher‑alignment schedule injects the linear branch into a pretrained MiniMax H3 model, preserving Softmax for text/audio streams. On eight NVIDIA B200 GPUs VDN‑H3 denoises a 14.3‑…
The authors present VākQA, a 2,001‑question spoken factoid QA benchmark for Telugu with audio, transcriptions, and human‑verified answers, and they validate automatic evaluation methods against human ratings. Using this setup they show that translation loses cultural nuance, ASR errors alter meaning, and cascaded ASR‑MT errors degrade model performance.
A detailed, personal review of Paul McKenney’s free online textbook on parallel programming. The author, coming from a TLA⁺/distributed‑systems background, finds the early chapters excellent for building intuition about CPU caches, memory ordering, and false‑sharing, but notes gaps (e.g., shallow coverage of C++11 atomics and MESI). The review is concrete, cites specific chapters, and offers prac…
Fathom introduces a per-query read depth mechanism for sparse decoding over offloaded KV caches, allowing each query to adaptively decide how many bits of each key channel to read. This method significantly speeds up decoding for large language models with long contexts by reducing host memory traffic, achieving 1.67x faster GPU decoding on Qwen3-8B at one million tokens.
The paper presents GameHorizon, a unified suite comprising an automated annotation pipeline, a 5,000‑hour multi‑horizon gameplay dataset from 21 AAA titles, and reproducible offline and online benchmarks. Using it, the authors evaluate 47 models, exposing a hierarchy of task difficulty and gaps in long‑term planning.
A concise walkthrough of the depth‑division trick for 3D projection, how it maps to the full perspective projection matrix, and GLSL snippets showing both the minimal trick and a proper matrix‑based camera.
OmniVChat defines native audio‑visual dialogue where a model consumes raw audio and video streams and replies in text. The authors build OmniVChat‑Studio, a multi‑agent simulator that generates single‑ and multi‑turn audio‑visual conversations, and use it to create OmniVChat‑Bench, a benchmark covering five dialogue abilities. They also propose OmniVChat‑RL, a reinforcement‑learning reward that b…
A practical guide to setting up a Gemini‑based blog (gemlog), covering platform choices, folder layout, naming conventions, optional features like favicons, security.txt, and interactive primitives using TLS client certificates.
A marketing‑focused announcement for Flat.social, a browser‑based 3‑D spatial meeting platform that lets users walk around, talk via spatial audio/video, and run virtual events. The post contains only product descriptions and user praise, with no technical implementation details, architecture, or performance data.
This post details a year of significant updates to w64devkit, a Windows development kit, including enhanced release security with code signing and immutability, and a multilib x64 toolchain. It also introduces new build tools like CMake, Ninja, and Ccache, alongside a custom C11 threads implementation and improvements to Binutils and GCC.
FAMOS is a feed-forward model that predicts 3D articulation, including movable-part segmentation and joint parameters, from sparse, unordered point clouds. It leverages multiple observations through a Multi-state Articulation Transformer and a novel observed articulation span objective, outperforming existing baselines.
WeVisDoc introduces a two‑stage data‑centric pipeline for end‑to‑end document parsing. Stage I expands coverage using heterogeneous data and structure‑preserving degradations. Stage II probes the Stage I model with a held‑out set, clusters residual errors, and directs targeted data creation and token‑budget reallocation. The 4‑billion‑parameter model reaches 95.38 Overall on OmniDocBench v1.6 and…
Go 1.27 adds a set of span‑class‑specific malloc functions for allocations ≤ 80 bytes. By generating a tiny, constant‑size allocator per span class the runtime can inline size‑dependent work (e.g. zero‑clear) and skip span‑class lookup, yielding 20‑30 % faster small allocations and ~1 % overall speed‑up for allocation‑heavy programs. The implementation is generated automatically via an AST inline…
VA‑Bench is a new benchmark that evaluates general‑purpose multimodal LLMs on the full observe‑reason‑act‑revise loop in embodied robotics, using RGB demonstrations, active camera control, and metric Cartesian commands. The best model reaches 53.9% average task success, showing active perception helps but long‑horizon tasks remain unsolved.
