2026年10月25日 技术热点总结

项目简介：Unlock FP/BF16 instruction issue rate on Nvidia 3000’s cards to their professional equivalents

技术栈：C

核心介绍：Unlock FP/BF16 instruction issue rate on Nvidia 3000’s cards to their professional equivalents This Linux kernel module combines the CMP unlocker’s V67/PLM technique with the pre-driver timing of the UEFI approach. It runs the unlock, writes the speed selectors (SS0 0x88888888, which selects the full BF16 rate, and the 4-bit SS1 0x8 IMLA4) and performs FLR before the unmodified NVIDIA driver binds the card. It is neither a UEFI application nor a patched NVIDIA driver….

项目简介：Extract huge archives in place: the archive shrinks as your files hatch, so you only need room for the output. ZIP, 7z, tar, split archives.

技术栈：Rust、7z、archive、cli、crash-safe、disk-space、extract、extractor、gui

核心介绍：HatchZip Extract huge archives in place. The archive shrinks as your files hatch, so you only need free space for the output, not for the output and the archive. Installation | Usage | Safety | How it works | Contributing

项目数据：⭐ 1,695 Stars，🍴 40 Forks

项目简介：Capture iPhone LiDAR and photos, reconstruct editable Three.js rooms, and explore them in a browser.

技术栈：Swift

核心介绍：Capture a room on an iPhone, then use its geometry and photographs to build an editable Three.js scene with an AI coding agent. Open the office viewer · App support This repository includes the 3D Model Anything iPhone app, a Three.js viewer, the scan-to-threejs agent skill, and Wes’s detailed office demo.

项目数据：⭐ 1,640 Stars，🍴 255 Forks

Robots must act under physical and social constraints while adapting to changes in their environment and human needs. Existing embodied-agent systems often focus on specified goals or abstract execution into symbolic actions, limiting evaluation in an evolving world. We introduce TARSphere, a robot-oriented full-stack framework for physically and socially grounded long-horizon embodied agents. TARSphere-Infra runs robot policies in a physics simulator with embodied NPCs and constrained dialogue. An event-driven finite-state machine (FSM) uses completed actions and delivered information to u…

Split language models keep input text on a client but send intermediate representations to a server. Attacks can reconstruct text from these messages. Comparing privacy evaluations is difficult when attackers see different messages, know different model weights or use different datasets and recovery measures. We present LLM-Attacker, a framework that records these choices and lets researchers check, compare and extend an evaluation. Compatible attacks reuse recorded messages, and their predictions are saved for independent scoring. The scoring rule requires a linked undefended reference bef…

Recursive self-improvement (RSI) relies on evaluation feedback to assess progress and guide further research, yet repeatedly running complex benchmarks is costly and slows iteration. Human experts reduce this cost by selecting benchmark subsets or designing compact suites. We ask whether AI agents can automate this design process and introduce EvalResearchBench (ERB), a benchmark for autonomous evaluation research. Given target materials, development references, candidate APIs, and fixed time and API budgets, an agent called the researcher selects or synthesizes tasks, implements graders, a…

Diffusion language models can write several tokens in one forward pass, and they decide during generation how many passes to spend. Two outputs of the same token length can therefore vary a lot in cost. To understand the underlying factors of this cost variation, we analyze two diffusion models across 10 tasks. We find that the number of forward passes per token depends heavily on the task. Text copied or lightly edited from the input is cheap, while open-ended writing is costly. In DiffusionGemma, generating a token for story writing requires more than three times as many forward passes as…

Diffusion Language Models (DLMs) introduce unique quantization challenges due to their iterative denoising process. In this work, we reveal that quantization sensitivity is both taskand time-dependent, with different downstream tasks exhibiting distinct precision requirements across denoising steps. We further show that these patterns can be predicted without groundtruth labels or task-specific evaluation metrics. Building on these findings, we introduce T 2Quant, a task and time-aware mixedprecision quantization framework that uses a label-free sensitivity signal to optimally allocate acti…

Effective test-time personalization requires LLM agents to adapt to query-dependent user preferences from lightweight interaction. We study persona selection with binary comparisons between candidate responses as the online signal. We present ID-TAP, a scalable, IDS-inspired neural dueling-bandit framework for large discrete persona spaces. ID-TAP combines a query-conditioned neural utility model with a lightweight Bradley-Terry explorer, and transfers comparison evidence across related queries through similarity-weighted warm starts. The neural model shares statistical strength across quer…