Self-Preservation in Language Models
arXiv:2610.12602v1 Announce Type: cross Abstract: Continual learning (CL) seeks to adapt pretrained models while preserving prior capabilities. Yet the tasks supplied for preservation cover only part
Knowledge catalogue
arXiv:2610.12602v1 Announce Type: cross Abstract: Continual learning (CL) seeks to adapt pretrained models while preserving prior capabilities. Yet the tasks supplied for preservation cover only part
arXiv:2610.13730v1 Announce Type: new Abstract: Origin-destination (OD) flow forecasting supports urban mobility decisions by predicting the volume and patterns of human movement across a city. Most e
separating artifacts from the agent makes sense for sharing and cross-AI collaboration No vendor lock-in for your artifacts. Sites, decks, 3D games, reports, dashboards and galleries. Artifacts on Fly
arXiv:2610.12975v1 Announce Type: new Abstract: We present SmartSalesBench, the first multi-turn conversational benchmark explicitly designed to evaluate large language model (LLM) sales agents agains
arXiv:2610.13740v1 Announce Type: cross Abstract: World-action models (WAMs) predict a robot's actions together with the observations those actions will produce. However, the strongest models rely on
arXiv:2610.03994v2 Announce Type: replace-cross Abstract: VeriContest is a benchmark of 1007 competitive-programming problems in Rust, each with a Verus specification, a judge-accepted solution, and a
Bloomberg: Sources: DeepSeek agrees to lead robotic AI startup Winverse AI's seed funding round of tens of millions of dollars, valuing the startup at ~$400M post-money — DeepSeek aims to lead the fir
arXiv:2610.12696v1 Announce Type: new Abstract: Vision-language-action models (VLAs) offer a promising route toward general-purpose robotics by transferring semantic knowledge from large-scale vision-
arXiv:2610.13812v1 Announce Type: new Abstract: Flow-matching and diffusion models are increasingly used as priors for linear inverse problems, however, most methods are bespoke to one class of trajec
arXiv:2610.12596v1 Announce Type: new Abstract: Agentic large language models now tackle complex tasks, yet strategic reasoning over long horizons is under-studied: most agentic benchmarks are short a
arXiv:2610.13461v1 Announce Type: new Abstract: AI systems are making rapid progress in mathematics, but this progress is hard to measure. Benchmarks of solved problems saturate, and in benchmarks of
arXiv:2610.12744v1 Announce Type: new Abstract: Parameter-efficient continual learning updates a restricted subset of adapter parameters to incorporate sequential tasks while limiting catastrophic for
I've been tuning llama.cpp on my Strix Halo box (Radeon 8060S, 128 GB) and the numbers are good enough to share. It's a branch called rdna35-perf on top of halo-box/strix-llama.cpp, a llama.cpp fork a
arXiv:2610.13306v1 Announce Type: new Abstract: Local online training on resource-constrained platforms requires low computational and training-state overhead. We study the numerical stability and com
arXiv:2610.13626v1 Announce Type: cross Abstract: Large Language Models (LLMs) are increasingly used throughout the software development lifecycle. This growing reliance on LLMs raises concerns about
arXiv:2610.12569v1 Announce Type: new Abstract: Static coding benchmarks are fixed at release. Over time their tasks leak into training data, and stronger agents eventually saturate them. We argue tha
arXiv:2610.13818v1 Announce Type: new Abstract: Representations of supervised datasets support higher-level machine-learning tasks such as dataset retrieval and distribution-shift monitoring. However,
arXiv:2610.13654v1 Announce Type: new Abstract: Tabular foundation models (TFMs) are increasingly popular for their strong predictive performance. Many also provide posterior predictive distributions
arXiv:2610.13325v1 Announce Type: cross Abstract: Agentic workloads resend long contexts that barely change between calls. Prefix caching now skips most of their prefill, yet every request must still
arXiv:2610.13895v1 Announce Type: cross Abstract: Large language models reuse the same attention heads across tasks, but identifying these shared heads does not explain what they do differently in eac
arXiv:2610.12874v1 Announce Type: new Abstract: Long-term memory has been widely adopted in LLM-based agents to support persistent interaction and personalized assistance. Long-term multi-party intera
arXiv:2406.07177v2 Announce Type: replace Abstract: Large language models (LLMs) have achieved remarkable performance on Natural Language Processing (NLP) tasks, but they are hindered by high computat
arXiv:2610.13036v1 Announce Type: new Abstract: Evaluating deep learning optimizer is challenging because confounding factors such as hyperparameter tuning and optimizer-model co-design often obscure
arXiv:2610.12806v1 Announce Type: cross Abstract: We study byte-level autoregressive language models whose hidden state is a small quantum register, whose transitions are learned token-conditioned qua
arXiv:2610.12747v1 Announce Type: cross Abstract: Ego-trajectory prediction in urban roadway work zones remains an underexplored topic in autonomous-driving research, with limited dedicated data and s
arXiv:2610.13690v1 Announce Type: new Abstract: Diffusion models typically learn the generative dynamics of a single target distribution or a family of distributions indexed by conditioning variables
arXiv:2610.13058v1 Announce Type: new Abstract: Large language model agents increasingly operate in long-horizon environments where early mistakes can trigger cascading failures and trap agents in dea
arXiv:2610.12828v1 Announce Type: new Abstract: Outcome-supervised group-relative policy optimization (GRPO) assigns the same advantage to every token in an LLM agent trajectory, leaving useful and un
As a business intelligence user, this probably sounds familiar: Most dashboards only provide you with a standardized canvas and a fixed library of charts, and the “analysis” consists of a CSV export t
arXiv:2610.12474v1 Announce Type: cross Abstract: Zero-shot text-to-speech (TTS) can clone a voice from seconds of audio. Yet the quality comes from billion-parameter diffusion transformers whose size
arXiv:2610.12742v1 Announce Type: new Abstract: This paper details our submission to KnowledgeGraphEval 2026 Subtask 2 on directed Arabic relation extraction. We explored encoder-based and large langu
arXiv:2610.13783v1 Announce Type: new Abstract: Memes play a central role in modern online communication, especially in contexts of political conflict where visual and textual cues combine to convey p
arXiv:2610.12863v1 Announce Type: new Abstract: Satirical news is a unique form of misinformation: it is intended to be humorous by the original publication source but can be misinterpreted. Explanati
arXiv:2610.12707v1 Announce Type: cross Abstract: Vision-language reward models are trained on annotated preference pairs, which are expensive to collect, can disagree, and are ranked by benchmark acc
What's Changed llama: update llama.cpp to b11521 for decision models and EmbeddingGemma 2 by @jmorganca in #18917 server: reuse verified manifests and loaded models in inference routes by @dhiltgen in
Inspired by DigUp for macOS, VectorDash aims to be a full Windows 11 search replacement, powered by EmbeddingGemma 2. Full indexing: search by meaning or exact words across photos, screenshots, audio,
arXiv:2610.13098v1 Announce Type: new Abstract: Visual agents for symbolic graphics reasoning depend on executable world representations, yet continued improvement remains bottlenecked by ambiguous su
arXiv:2610.13689v1 Announce Type: new Abstract: Learning how local perturbations affect a network is important for identifying which components drive or absorb a system's response. We formulate this a
arXiv:2603.17917v2 Announce Type: replace-cross Abstract: Large language models (LLMs) contain billions of parameters, but many exact weight values are not essential. We apply scalar K-means clusterin
Ive been using OpenWebUI's inbuilt web search and I can't put my finger on it, but it's not quite as polished, reliable, seamless as using Claude or Gemini. And its often slow beyond a limit that make
arXiv:2610.12561v1 Announce Type: new Abstract: Memory allows large language model (LLM) agents to use past experience, often stored as textual records, when responding to requests. For embodied agent
arXiv:2610.12823v1 Announce Type: new Abstract: Web agents increasingly browse, interpret, and act on web content on behalf of users. In many realistic workflows, however, the visual evidence they con
arXiv:2610.13788v1 Announce Type: new Abstract: LiDAR-inertial odometry (LIO) is widely used for real-time localization and mapping, but its reliability can degrade substantially in subterranean envir
arXiv:2605.11928v2 Announce Type: replace Abstract: Tool-use language agents are evaluated on benchmarks that assume clean inputs, unambiguous tool registries, and reliable APIs. Real deployments viol
arXiv:2610.13910v1 Announce Type: new Abstract: Vision-Language Models (VLMs) increasingly analyze and reason about images, yet it remains unclear whether their internal representations faithfully enc
arXiv:2607.09996v2 Announce Type: replace Abstract: Automated failure attribution uses LLMs to identify where and why agentic systems fail. As agents become more capable, their failures become subtler
arXiv:2610.13123v1 Announce Type: cross Abstract: A solid understanding of the predictive success of deep neural networks (DNNs) remains elusive. For example, while many data-dependent metrics exist t
With only ~$1,000 of training compute, we trained 𝗳𝗿𝗼𝗺 𝘀𝗰𝗿𝗮𝘁𝗰𝗵 a 1.7B coding agent that beats Claude 3 Opus and GPT-4o on SWE-bench Verified 🤯 At 25.5% pass@1, it sets a new record for nanoswe, our op
world’s first full length workshop on claude flows @cjav_dev and Harrison Stall are kicking off @aidotengineer bright and early on a monday morning to a PACKED room, standing room only #AIEngineerNY @
arXiv:2504.06185v3 Announce Type: replace-cross Abstract: Chronic wounds affect a large population, particularly the elderly and diabetic patients, who often exhibit limited mobility and co-existing h
Zai recently launched a domain‑specific language model called **GLM Legal**. According to a tweet posted at 4:13 PM on Oct 12, 2026, GLM Legal became the leading open‑weight model on both **Harvey’s L
A new work suggesting that division of labor among self-improving AI agents can help them avoid reinforcing their own errors. I found this work interesting from a metascience perspective. Science is a
Anatomy skill for building wireframe designs and interactive prototype machines is now an officially integrated optional skill in Hermes Agent You can find it in the optional built in skills in the sk
server: add component tests (#30312) server: add component tests nits add codeowners Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/54782864 macOS/iOS: mac
vulkan: handle mul_mat_id duplicates in the prepass rather than looping (#29998) vulkan: compute every row of an expert in mul_mm_id when ids repeat vulkan: handle mul_mat_id duplicates in the prepass
cpu: fix AVX2 CPUs not using F16C when available (#30270) Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/54796975 macOS/iOS: macOS Apple Silicon (arm64) ma
model : support for Prism Bonsai 2 27B (#29600) Runtime support for Prism Bonsai 2 27B Assisted-by: Claude Code address prism hadamard runtime feedback move hadamard tensors into method, define folded
rpc : turn GGML_RPC_DEBUG into a verbosity level and add logs GGML_RPC_DEBUG is now parsed as a number: 0/unset disables debug logs, 1-3 emit increasingly detailed output (events, per-command trace, t
opencl: fix image limit for q4_k dense bin kernels, q4_0 bcast and rms_norm (#30310) opencl: fallback when Q4_K weight images exceed device limits Co-authored-by: Hongqiang Wang wangh@qti.qualcomm.com
opencl: improve fa, allow dk512 for gemma-4, improve dk64 (#30266) opencl: enable Gemma-4 E4B GPU decode Co-authored-by: Hongqiang Wang wangh@qti.qualcomm.com opencl: extend Gemma-4 GPU decode to E2B