arXiv:2611.17539v1 Announce Type: new Abstract: Autonomous crystal-structure determination from powder X-ray diffraction (pXRD) remains a key bottleneck for self-driving materials laboratories. We formulate the task of pXRD structure determination as a verifiable agentic search …
⏱ Độ trễ thật của tab này: trung bình 7.2 giờ sau khi CVE được công bố (n = 5387, sớm nhất 0.1 giờ). Số âm nghĩa là ta thấy trước ngày công bố.
🧩 Chức năng: Tìm kiếm/CSDL vector cho RAG
Xorbits Inference: nền tảng inference mã nguồn mở hỗ trợ language, vision, embedding, reranking, image, audio và video model. Triển khai trên nhiều engine, phần cứng từ laptop đến cluster phân tán, truy cập qua API tương thích OpenAI.
arXiv:2611.13696v1 Announce Type: new Abstract: Multi-agent systems provide a convenient framework for the massive deployment of agents based on Large Language Models (LLMs). It provides a sound framework where agents can interact with existing software to perform actions in an …
An attacker exploited a remote code execution flaw in SGLang, an open-source inference engine, and ran code on one of NEAR AI's inference servers last Sunday. The attacker could also have seen requests being processed on that server that day, including requests sent in confident…
🎯 Kẻ tấn công làm gì (từng bước)
- Tìm đúng đường dẫn/API có xử lý dữ liệu người dùng gửi lên
- Gửi payload đã chế để máy chủ thực thi lệnh/mã
- Dùng quyền của tiến trình web để đọc file, cài backdoor, mở kênh ra ngoài
🔍 Dấu hiệu bị tấn công (để kiểm tra log)
- Tiến trình web (php-fpm/nginx/java) sinh tiến trình con bất thường: sh, bash, curl, wget
- Kết nối ra ngoài từ máy chủ tới IP lạ đúng lúc có request lạ
- File mới xuất hiện trong thư mục tải lên/tạm
🛡 Phòng ngay (làm được hôm nay)
- Vá ngay bản có lỗi (ưu tiên số 1)
- Chặn tạm đường dẫn/API bị lỗi ở WAF/reverse proxy nếu chưa vá được
- Chạy tiến trình web bằng user quyền thấp, tắt các hàm shell (disable_functions) nếu dùng PHP
- Bật giám sát tiến trình con của web server để phát hiện lệnh lạ
arXiv:2611.17610v1 Announce Type: new Abstract: Evaluations of multi-agent language models often compare communicating architectures against a single greedy pass. This practice confounds coordination with sample multiplicity and inference compute. We synthesize nine primary empi…
🧩 Chức năng: Giọng nói / TTS — đọc văn bản, nhân bản giọng, lồng tiếng
VieNeu-TTS là công cụ chuyển văn bản thành tiếng Việt với khả năng nhân bản giọng nói tức thì, chạy trên thiết bị, suy luận CPU thời gian thực và chất lượng âm thanh 48kHz. Phù hợp cho các ứng dụng cần TTS tiếng Việt chất lượng cao offline.
< 1.1.0
Lỗ hổng SQL injection trong tham số 'where' của công cụ 'count_rows' thuộc pgEdge Postgres MCP Server. Kẻ tấn công có thể lợi dụng subquery để trích xuất dữ liệu trái phép từ các bảng khác mà database role có quyền truy cập.
🎯 Kẻ tấn công làm gì (từng bước)
- Dò tham số/ô nhập được đưa vào câu lệnh SQL
- Chèn câu SQL để thử (lỗi cú pháp, OR 1=1, UNION SELECT, sleep)
- Dùng UNION/stacked query để đọc bảng users, token, đôi khi ghi file để chiếm máy
🔍 Dấu hiệu bị tấn công (để kiểm tra log)
- Log web có chuỗi đặc trưng: UNION SELECT, ' OR 1=1, sleep(, information_schema
- Tăng đột biến lỗi CSDL 500 ở cùng một tham số
- Một truy vấn kéo về số dòng bất thường (dump dữ liệu)
🛡 Phòng ngay (làm được hôm nay)
- Vá plugin/CMS có lỗi (với WordPress: xoá plugin không dùng, cập nhật plugin bị ảnh hưởng)
- Bật WAF rule chống SQLi (OWASP CRS) ở chế độ chặn
- Tài khoản CSDL của ứng dụng chỉ có quyền cần thiết (không DROP/GRANT)
- Bật log chậm/truy vấn bất thường để phát hiện dump
Darktrace researchers turned Claude Code into a remote-controlled implant in a lab test, steering the coding agent through the memory stores feature of Anthropic’s Claude platform and pulling a 1 GB file out through the Claude Files API. Once the agent was set up, every job and e…
Small language models (SLMs) running on mobile devices can keep user data private and work without connectivity. But they perform well only when fine-tuned for the target task and sized for the target device, a process that today requires repeated expert tuning. We present {\it M…
arXiv:2611.17621v1 Announce Type: new Abstract: Kernel optimization is essential for efficient large language model (LLM) training and inference on Ascend NPUs. Existing Ascend kernel benchmarks primarily focus on kernel generation, with less emphasis on the ability of agents to…
arXiv:2611.18272v1 Announce Type: new Abstract: Existing memory forensics for machine learning systems typically targets static artifacts, such as model weights or prompt logs, rather than the transient computational states of a live inference process. This gap limits an examine…
🧩 Chức năng: Công cụ quanh mô hình ngôn ngữ (prompt/agent)
llama.cpp là thư viện mã nguồn mở tối ưu hoá việc suy luận (inference) các mô hình LLM viết bằng C/C++, giúp chạy mượt mà các model lớn trên đa dạng phần cứng như CPU, GPU và Apple Silicon.
Mô hình Qwen3.8-27B được tối ưu hóa với Unsloth, hỗ trợ định dạng GGUF giúp việc chạy suy luận (inference) trên các thiết bị consumer dễ dàng hơn. Phù hợp cho lập trình viên muốn thử nghiệm LLM hiệu năng cao mà không tốn nhiều tài nguyên.
arXiv:2611.14681v1 Announce Type: new Abstract: Today's AI workloads are rapidly changing: new models are released more often, model architectures are increasingly diverse, and traffic distributions change frequently. The challenge we face at Together AI is continual optimizatio…
arXiv:2611.17340v1 Announce Type: new Abstract: Large language models are expensive to update through full retraining. Parameter-efficient fine-tuning reduces the cost of adaptation, but repeated adaptation creates a growing pool of task-specific LoRA adapters. This pool complic…
arXiv:2611.17501v1 Announce Type: new Abstract: Recommendation and Ranking (R&R) models, particularly in digital advertising, require massive inference throughput but exhibit extreme sensitivity to precision loss. Unlike Large Language Models (LLMs) that frequently tolerate quan…
arXiv:2611.17524v1 Announce Type: new Abstract: A small labelled dataset is memorized long before the training budget runs out, and the one-hot labels that remain to be fitted then mostly sharpen confidence. Model annealing spends the rest of the budget on review and consolidati…
arXiv:2611.17620v1 Announce Type: new Abstract: High-level behaviors such as sycophancy and hallucination correspond to directions in a model's activation space (Chen et al., 2025). These directions, known as persona vectors, can suppress undesirable traits either at inference t…
arXiv:2611.18442v1 Announce Type: new Abstract: Open driving releases and usage-based insurance programs often claim to prevent privacy breaches by omitting GPS records when sharing or collecting vehicle data. However, removing GPS coordinates from driving logs does not erase th…
🧩 Chức năng: Làm game/engine
LLM Inference Engine for Metal, CUDA and Vulkan.
🧩 Chức năng: Làm game/engine
The open engine for running AI on your own computer. Fast, exact, open source.
arXiv:2611.15238v1 Announce Type: new Abstract: Discrete diffusion generation is emerging as a competitive alternative to autoregressive generation by denoising the entire token sequence through iterative refinement. Its global planning and progressive correction capabilities ar…
arXiv:2611.14984v1 Announce Type: new Abstract: Reward models (RMs) are increasingly deployed as service components in LLM alignment pipelines, where payment, audit, moderation, and governance workflows act on the scores they return. An inference proof alone does not show whethe…
arXiv:2611.16048v1 Announce Type: new Abstract: Personalized LLM services place private facts and application instructions into a prompt, then retain representations of that context for later inference. Latent-state LLMs compress part of this history into fixed-size recurrent st…
arXiv:2611.13641v1 Announce Type: new Abstract: Privacy concerns have been raised in Large Language Models (LLM) inference when models are deployed in Cloud Service Providers (CSP). Homomorphic encryption (HE) offers a promising solution by enabling secure inference directly ove…
arXiv:2511.13502v4 Announce Type: replace Abstract: In-context learning (ICL) enables LLMs to adapt to tasks using demonstrations that may contain sensitive data. Differentially private (DP) ICL mechanisms mitigate this risk by adding noise during aggregation. However, verifying…
Low-bit quantization reduces the inference cost of LLM agents but can compromise task success. Examining failed rollouts, we find that quantized agents overlook task requirements or environmental conditions, producing environment transitions that diverge from successful full-prec…
arXiv:2611.10193v1 Announce Type: new Abstract: Large language models (LLMs) increasingly support Web-based services that must balance response quality and inference cost across heterogeneous requests. Conventional routing selects one model per prompt, while fixed ensembles cann…
arXiv:2611.10165v1 Announce Type: new Abstract: Existing LLM post-training quantization techniques determine precision before inference begins, yet the precision a model requires varies dynamically across prompts, layers, and inference phases. We present AutoEMatic, a full-stack…
arXiv:2611.10418v1 Announce Type: new Abstract: Semantic response caching reuses a cached response for a semantically similar query to improve LLM inference efficiency. However, query similarity alone can lead to unsafe reuse when safety conditions change. Existing approaches im…
Hi everyone, I am troubleshooting recurring hard system freezes on my Proxmox VE node during heavy local AI workloads (Ollama/LLM inference) and would appreciate any insights into potential kernel, BIOS, or PCIe/chipset bottlenecks. Symptoms: Under sustained multi-GPU…
Open driving releases and usage-based insurance programs often claim to prevent privacy breaches by omitting GPS records when sharing or collecting vehicle data. However, removing GPS coordinates from driving logs does not erase the location information carried by vehicle signals…
🧩 Chức năng: Tạo/xử lý video bằng AI
SOTA model-agnostic quantization for GGUF, local inference and beyond. Quantize and run text, image, video and audio models with llama.cpp, vLLM, Diffusers and PyTorch.
arXiv:2611.14736v1 Announce Type: new Abstract: Observational causal discovery often leaves causal di- rections unresolved or unstable. Large language mod- els (LLMs) can provide semantic information to resolve these directions, but incorrect proposals can exclude the true causa…
arXiv:2611.14942v1 Announce Type: new Abstract: Does multimodal training shape how a language model thinks, even when the input is text only? We test this with targeted causal ablations across 10 multimodal configurations from 6 model families, with matched text-only backbones a…
arXiv:2611.15109v1 Announce Type: new Abstract: Native decoders limit how pretrained models combine local predictions under new structural constraints. We introduce Structured Re-Decoding (SRD), a training-free framework that constructs local candidates from model scores, sample…
arXiv:2611.16151v1 Announce Type: new Abstract: Hardware fault injection attacks threaten machine learning systems, yet their impact on reinforcement learning (RL) has received little attention despite the use of RL in safety-critical applications. This paper presents a security…
arXiv:2611.14083v1 Announce Type: new Abstract: We present Sable, an argument system and single-GPU prover for the statement that a committed, integer-quantized transformer produced a given token sequence from a given prompt, bit for bit. Sable fixes an integer function F_O with…
arXiv:2611.12937v1 Announce Type: new Abstract: Do large language models represent psychological constructs internally, or do they only generate outputs that resemble psychometric structure? We address this question using a cross-persona paradigm across 14 model variants from tw…