Knowledge catalogue
arXiv:2609.14820v1 Announce Type: cross Abstract: This work presents POLARIS, a training-free audio fingerprinting system that selects landmarks from a locally normalized saliency field and groups the
arXiv:2609.06327v2 Announce Type: replace-cross Abstract: A query-oblivious coreset for a softmax-attention head is a subset of the key-value pairs whose attention output is within arepsilon of the fu
arXiv:2609.13203v1 Announce Type: new Abstract: Pairwise relationships among mental-health symptoms are routinely summarised asscalar edge weights, which cannot express whether two symptoms carry over
Valida Pau / The Information: Source: AI assistant Instinct seeks to raise 1B at a 10B valuation, up from 2.25B less than a month ago; Sequoia and Benchmark are in talks to lead the round — The startu
arXiv:2609.13309v1 Announce Type: cross Abstract: Protocol optimization in computed tomography (CT) aims to improve diagnostic image quality while reducing radiation dose, but the interdependence of a
arXiv:2609.15921v1 Announce Type: new Abstract: Dexterous manipulation of deformable objects demands continuous fingertip-level regulation of pressure, friction, and incipient slip. We study one of th
arXiv:2609.15773v1 Announce Type: cross Abstract: Progress in inclusive household surveys has strengthened socioeconomic evidence for forcibly displaced populations, providing indispensable benchmarks
arXiv:2609.07474v2 Announce Type: replace Abstract: Language models compute over tokens: language is their input, their output, and increasingly their internal representation. Whether language should
arXiv:2609.12320v1 Announce Type: cross Abstract: Traditional large language models (LLMs) are scoped to individual user sessions, limiting their knowledge to a single conversation and preventing them
arXiv:2609.12086v1 Announce Type: cross Abstract: Assistants built on large language models are expected to write as their user would, and the dominant approach is single-channel: preferences summaris
Note - This is translated from the actual blog link right at the bottom. A few days ago, DeepSeek v4.1 was released. It raised the ability of small models to a new level. AI is improving much faster t
arXiv:2609.12678v1 Announce Type: new Abstract: Short-video platforms have become a primary news source for the public, which has also enabled the widespread dissemination of fake news videos. We stud
“Just-in-Time” OCR The latest agent harnesses (e.g. Cowork, Codex, Grok) do 2 passes of ad-hoc document processing when executing over a user-uploaded ‘data room’ of documents: 1️⃣ A fast and light pa
arXiv:2609.13040v1 Announce Type: new Abstract: We study loss-based filtering for finite-sum optimization with a subset of corrupted component functions whose gradients may be highly unreliable. Motiv
Marissa Newman / Bloomberg: US-Israeli startup Buildots, which uses AI to speed up construction of mega-projects like data centers and chip factories, raised 130M at a near-1B valuation — Buildots, a
Overview llama.cpp 0.4.1 adds Maple 20B-A1B, Tencent Hy 4, and Spark2.5 support, improves JSON schema handling, chat parsing, logging, and server child-process management, and updates ggml to v0.24.0.
Automated lint: 12 errors, 54839 warnings, 3 info
arXiv:2609.11542v1 Announce Type: new Abstract: Large language model (LLM) training is among the fastest-growing sources of electricity demand in modern data centers, and power availability is a prima
Fast meets open. 🚀 Qwen3.8-27B is now running on @cerebras with rapid inference. Try it now! Qwen3.8-27B is now live at Cerebras speed. The dense, open-weight model from @Alibaba_Qwen scores 34 on the
arXiv:2609.10724v1 Announce Type: new Abstract: Sustained deployment of generative AI agents requires more than isolated task success. Agents must remain useful across repeated interactions, changing
arXiv:2609.11065v1 Announce Type: new Abstract: Graph Retrieval-Augmented Generation (GraphRAG) can connect evidence distributed across a corpus graph, but most systems use largely shared exploration
Self-improving agents are a top research topic right now. This new survey is a good map of the area. (bookmark it) It splits recursive self-improvement into stages of autonomy. An agent first executes
arXiv:2609.10830v1 Announce Type: new Abstract: When a language model finds a sentence unusually cheap to predict, it is tempting to conclude that the sentence was in its training data. Almost every p
arXiv:2609.10892v1 Announce Type: cross Abstract: When an indirect prompt injection succeeds against an LLM agent, the compromise is visible in the agent's own behavior: a benign prefix of tool calls,
Last Friday night, our team hosted a lit event at the US Open 🎾 we gathered a group of enterprise and startup AI leaders + founders together to drink, talk about AI and document parsing, and watch ten
arXiv:2609.11449v1 Announce Type: new Abstract: Many ML datasets are constructed by running a detector, heuristic, or model over candidate pools; accepted items become labels. Dataset precision is the
arXiv:2609.11650v1 Announce Type: new Abstract: Accurate identification of end-diastole (ED) and end-systole (ES) in echocardiography underpins the quantification of ventricular function, yet manual s
arXiv:2509.25741v3 Announce Type: replace-cross Abstract: Test-time training (TTT) enhances model performance by explicitly updating designated parameters prior to each prediction to adapt to the test
arXiv:2609.11873v1 Announce Type: cross Abstract: Recursive self-improvement (RSI) enables AI systems to turn experience and feedback into persistent changes that improve both their capabilities and t
arXiv:2609.11146v1 Announce Type: cross Abstract: AI-generated text is flowing back into the training corpora of the next generation of models. Recursive training on it drives model collapse, and rece
arXiv:2609.10263v1 Announce Type: new Abstract: Persistent language agents need stored experience to remain available across time, while each answer requires evidence suited to a particular question.
Like many of you, I have seen many posts and tweets in the last weeks complaining about Artificial Analysis being 'broken', 'meaningless', and 'bought out.' People who say this have done no research a
arXiv:2609.09904v1 Announce Type: new Abstract: Federated clients that perform several local optimization steps can return parameter displacements with widely different magnitudes. The quadratic regul
arXiv:2609.07050v1 Announce Type: new Abstract: Retrieval-augmented generation (RAG) critically depends on retrieving the evidence necessary for effective reasoning. However, this remains particularly
arXiv:2609.09510v1 Announce Type: cross Abstract: High-risk non-muscle-invasive bladder cancer (HR-NMIBC) carries substantial risks of recurrence and progression, while current clinical risk stratific
Reuters: DeepSeek debuts DeepSeek-V4.1-Flash, its smallest model built on its new Causal Encoder-Decoder architecture, with 552B backbone parameters and 1M-token context — Chinese artificial intellige
arXiv:2609.08407v1 Announce Type: new Abstract: In this study, we identify depth-dependent prefix redundancy in final-readout LLM embedding models, notably across representative backbones including Qw
arXiv:2609.09573v1 Announce Type: cross Abstract: Odor quality is commonly represented using high dimensional descriptor profiles, yet their low dimensional organization remains unclear. We investigat
arXiv:2609.07598v1 Announce Type: cross Abstract: Large language models (LLMs) increasingly shape communication, learning, work, creativity, and decision-making, yet social-science research on these d
arXiv:2609.08273v1 Announce Type: new Abstract: Agent memory systems have demonstrated significant potential in long-term dialogue, personalized assistants, and video understanding. However, continuou
arXiv:2609.09984v1 Announce Type: new Abstract: Understanding the historical allocation and distribution of research funding advances our knowledge of how scientific research is supported across field
arXiv:2609.06127v1 Announce Type: cross Abstract: Retrieval-augmented generation is usually formulated as a statistical information-retrieval problem. Graph-based variants add relational structure, bu
arXiv:2505.00225v2 Announce Type: replace Abstract: Utilities publish Estimated Times of Restoration (ETRs) for customer-facing storm outages, and their accuracy governs whether customers can make sou
arXiv:2609.07910v1 Announce Type: new Abstract: Multi-agent federations need governance that answers three questions under adversarial conditions: who participated (identity), did they conform (enforc
arXiv:2609.09368v1 Announce Type: new Abstract: We present the Living Library, an end-to-end framework for transforming fragmented digital archives into governed, conversational, in-person exhibit exp
arXiv:2609.09854v1 Announce Type: cross Abstract: Low-bit quantization can achieve high recall on some vector representations and fail sharply on others, while average distortion and global rank corre
arXiv:2609.09388v1 Announce Type: new Abstract: Brain-age prediction models are commonly evaluated by predictive accuracy, yet accurate predictions alone do not establish that a model relies on reprod
arXiv:2609.06008v1 Announce Type: cross Abstract: We present Cadence, an error-bounded lossy compressor for numeric time series pairing a 330M-parameter time-series foundation model (Google TimesFM-3)
arXiv:2609.07561v1 Announce Type: cross Abstract: Late-interaction models such as ColBERT achieve strong effectiveness by representing each document with many token-level vectors, but this expressivit
arXiv:2609.05744v1 Announce Type: new Abstract: Reconstructing continuous terrain manifolds from massive, unstructured airborne LiDAR point clouds remains challenging in complex Wildland-Urban Interfa
arXiv:2609.08796v1 Announce Type: new Abstract: Multi-agent traffic simulation seeks diverse, coordinated, and physically realistic futures from maps and observed history. Long-horizon closed-loop gen
Last week we brought LlamaParse to Claude. Now it’s available in ChatGPT, too 🦙 ChatGPT can already read PDFs. But document work gets harder when the information you need is buried in messy scans, den
Automated lint: 12 errors, 53990 warnings, 3 info
Nice paper to improve inference efficiency. It's been a while we haven't seen good work on efficiency. Here is why it matters: A long-running agent's workspace outgrows its context window long before
arXiv:2609.06521v1 Announce Type: new Abstract: Oversmoothing is a well-known failure mode of Graph Neural Networks (GNNs). However, most existing diagnostics rely on global aggregation measures that
arXiv:2606.14199v2 Announce Type: replace-cross Abstract: Large language models are increasingly deployed as human simulators for interactive evaluation and social simulation. Yet helpfulness-driven p
arXiv:2609.05661v1 Announce Type: new Abstract: We present Srijika, a system for producing installable OpenType fonts for nine Brahmic scripts: Devanagari, Tamil, Bengali, Telugu, Kannada, Malayalam,
arXiv:2609.06788v1 Announce Type: new Abstract: Automatic Pronunciation Assessment (APA) systems have achieved strong performance with transformer-based models and self-supervised speech representatio
John Koetsier / Forbes: Antioch, which creates high-fidelity simulations to reduce the need for hardware validation in physical AI training, raised a $32M Series A led by Greylock — Figure AI pulled t
An update to my previous post on running Flash-Next with the expert cache and MTP. I found another useful improvement on the same dual-3090 setup: replacing the CUDA top-k fallback used by my build. O