2026年9月23日 技术热点总结

项目简介：装在手机上的对话副驾：在微信 / QQ / X / 飞书里读懂对方、给出候选回复、一键填入输入框，发不发由你。非侵入，只读屏幕，不 hook 不改包。

技术栈：Kotlin、accessibility-service、android、chat-assistant、llm、qq、wechat

核心介绍：官网 · 下载 APK · 历史版本 · 更新日志 · macOS 版 · Windows 版 > 想出现在这里？ 点击折叠 感谢 小优店铺 赞助了本项目！小优店铺是一家数字商品与账号服务店铺，为本项目的用户提供选购渠道。点此前往。 感谢 速创猫 Vytal 赞助了本项目！速创猫 Vytal 专业的 AI 视频工作流平台，可批量复用的视频工作流，降低内容制作门槛，服务内容创作者、培训机构及中小团队。点此前往。 悬浮窗：危险等级、对方真实意图、排好序的 3 条候选回复 设置页：判断 / 回复 / 视觉三路接口分别可配

项目数据：⭐ 3,723 Stars，🍴 830 Forks

项目简介：Local Laya typed decisions on Apple Core ML and Neural Engine. Validated ports, ~5 ms short decisions on M3 Max, reproducible speed and energy benchmarks.

技术栈：Python、apple-neural-engine、apple-silicon、coreml、decision-model、laya、local-ai、modernbert、on-device-ai

核心介绍：PyPI · Hugging Face weights · 中文 A real Laya model plays Snake locally, with visible probabilities, score, length, latency and safety interventions. The GIF replays a recorded Core ML run at 1× speed. The game uses explicit planner features and a visible cycle safety layer. The complete active Snake loop sus…

Reinforcement learning (RL) has become a key technique for improving the reasoning and agentic abilities of large language models (LLMs). Although FP8 quantization can accelerate RL training, maintaining stability throughout an FP8 RL pipeline remains challenging. While previous works have focused on resolving train-inference mismatches using correction techniques like TIS, we reveal that full-pipeline FP8 RL still suffers from severe training instability, manifesting as anomalous mid-training entropy surges and garbled outputs. We trace this instability to a previously overlooked cause: co…

Building general-purpose agents for industrial deployment requires integrating multiple capabilities, each typically acquired at a distinct stage of training. Yet there is currently no well-established recipe for Agent Continual Learning (ACL), with little understanding of the trade-offs among existing integration paradigms. To address this gap, we introduce ACLArena, a framework for comprehensively studying, analyzing, and evaluating ACL. We first build a sequential training pipeline and conduct an in-depth analysis that explains the mechanisms of forgetting and generalization from two com…

Autonomous agent systems increasingly depend on reusable skill abstractions for consolidating experiential knowledge and domain expertise. These artifacts typically bundle free-form instructions with heterogeneous resources. However, ensuring their correctness remains challenging. Their failure modes transcend conventional code defects to subtle semantic inconsistencies such as intent conflicts, which manifest as silent failures masked by the underlying model. Moreover, skill correctness must be grounded in intended task boundaries and generalizability. We propose SkillSpec, a Hoare-style f…

Standard subword tokenizers either treat every orthographic variation of a word (such as hello, Hello, HELLO, and Héllo) as unrelated vocabulary entries, which fragments the embedding space, or discard this variation through lossy normalization. We present the Functionalizer, a lossless pre-tokenizer framework that factors orthographic and structural variations into a compositional opcode/operand prefix stream before tokenization: a canonical base token (operand) prefixed by parametric transformation operators (opcodes) encoded in the Unicode Private Use Area. We introduce operators coverin…

Natural interaction in digital and physical environments requires continuous perception and timely responses. Spoken dialogue relies on acoustic and linguistic cues, while video interaction also requires grounding the conversation in evolving visual context. We present Realtime-Venus, a proactive full-duplex interaction system with two separately trained 9B models: Realtime-Venus-Omni for audio-visual interaction and Realtime-Venus-Audio for spoken interaction. Each model serves as a complete conversational frontend, integrating continuous perception, conversational control, and native spee…

High-quality texture generation is essential for creating realistic and production-ready 3D assets. Recent multi-view diffusion methods have shown promising results for image-guided 3D texturing, but they are typically constrained to low operating resolutions such as 512 or 768, making it difficult to preserve high-frequency details from high-resolution reference images. Scaling this paradigm to 2048 resolution is computationally prohibitive, as the unified multi-view sequence exceeds 212K tokens and incurs excessive memory and latency. In this paper, we present UltraTex, an efficient end-t…