Knowledge catalogue
After many years in top machine learning organizations, with friends at frontier labs, I still consider Tesla’s ML engineers the best—the only ones I would trust with my life. Unsatisfied with theory,
arXiv:2610.08775v1 Announce Type: new Abstract: Large language models (LLMs) can solve many narrow tasks, but querying them separately for millions of related instances can be prohibitively expensive.
Training AI agents with reinforcement learning can be challenging because their tools, context, and decision-making are managed by complex frameworks. Agent Lightning connects existing agents to RL tr
Agent-to-agent communication with a personal agent on top is wild. Wow. I underestimated how well models like Opus 5.5 can coordinate already. This opens a whole new set of experiences with agents. Bu
arXiv:2610.04188v2 Announce Type: replace Abstract: Recent studies show that artificial intelligence (AI) with language and vision capabilities still experiences limitations in spatial reasoning. In t
arXiv:2610.08452v1 Announce Type: new Abstract: Retrieval-augmented generation (RAG) is a widely used approach for grounding large language models (LLMs) in external knowledge. However, configuring a
arXiv:2610.07191v1 Announce Type: cross Abstract: Modern edge Systems-on-Chip (SoCs) integrate heterogeneous processing units (PUs) such as CPUs, GPUs, and NPUs, each with distinct performance and ene
arXiv:2610.08622v1 Announce Type: cross Abstract: System administrators of Internet-scale services need to resolve failure incidents to maintain reliability of such services. Ideally, we want a troubl
arXiv:2610.07829v1 Announce Type: new Abstract: Semantic sensing (SemS) acquires task-relevant information rather than reconstructing complete physical information. Existing SemS formulations typicall
arXiv:2610.07707v1 Announce Type: new Abstract: Conversational AI assistants with long-term memory extract facts from user messages into a store consulted in later conversations. A stated plan can ent
arXiv:2610.07128v1 Announce Type: cross Abstract: Aggregating the preferences of diverse user groups into a collective outcome raises fundamental challenges of equity, diversity, and inclusion (EDI):
arXiv:2610.08703v1 Announce Type: new Abstract: In K-12 mathematics tutoring, student-tutor dialogue provides rich evidence of learners' problem-solving processes and sources of difficulty. Learning a
arXiv:2610.01108v2 Announce Type: replace Abstract: Retrieval-based speculative decoding (SD) drafts tokens by copying continuations from existing text, which suits coding agents that repeatedly repro
AI is getting REALLY good at building your wardrobe. I built an app with GPT-6 Astra that picks my outfit every morning based on live weather, with me as the model. It's super simple to do: > Upload a
Mary Ann Azevedo / Crunchbase News: AI startup acquisitions by AI startups hit 195 through September 29, up 14% from all of 2025, but the number of buyers grew just 2%; OpenAI was the most active — So
arXiv:2610.07116v1 Announce Type: new Abstract: Deformable-object manipulation is essential for robotic tasks such as folding laundry and handling food, where robots must control shape changes as well
arXiv:2610.07566v1 Announce Type: new Abstract: Feed-forward novel view synthesis methods achieve strong generalization from posed multi-view inputs, but scaling them to large input view sets remains
arXiv:2610.07271v1 Announce Type: new Abstract: Linkage algorithms for hierarchical clustering (HC) are a powerful and efficient framework for constructing clustering trees, yet it is often unclear wh
arXiv:2610.08164v1 Announce Type: cross Abstract: Low-rank quantization error compensation (LQEC) recovers the accuracy lost under aggressive weight quantization by attaching a closed-form rank-r adap
arXiv:2610.07457v1 Announce Type: cross Abstract: Fine-grained mixed-precision quantization promises efficient large language model inference, but local precision choices can conflict with regular GPU
arXiv:2610.08779v1 Announce Type: new Abstract: Current video editors can insert objects but often struggle to make them participate in interactions such as being picked up or manipulated. We introduc
arXiv:2610.07819v1 Announce Type: cross Abstract: Model merging offers a promising solution for combining multiple fine-tuned checkpoints into a single model through parameter arithmetic. However, fin
arXiv:2610.07118v1 Announce Type: new Abstract: Modern language-model agents increasingly interact with external environments over long-horizon, multi-step trajectories, where the accumulated interact
arXiv:2610.08329v1 Announce Type: new Abstract: We present an AI-assisted Lean 4 formalization of the Poincare conjecture. The project began with limited reusable formal infrastructure for the geometr
arXiv:2610.07398v1 Announce Type: new Abstract: Versatile, autonomous robotic boats can offer excellent environmental inspection and monitoring solutions for remote, dangerous, hard to reach, or acces
arXiv:2610.07029v1 Announce Type: cross Abstract: Resistive random-access memory (ReRAM)-based Processing-in-Memory (PIM) accelerator is a promising platform for processing massively memory intensive
arXiv:2610.06988v1 Announce Type: new Abstract: Knowledge tracing (KT) models are predominantly evaluated using aggregate metrics such as area under the curve (AUC) and accuracy. However, these global
arXiv:2610.07211v1 Announce Type: cross Abstract: Systems of equations arise in a wide range of scientific and engineering applications. The present work focuses on solvers for general systems of equa
arXiv:2610.07016v1 Announce Type: cross Abstract: In few-shot industrial anomaly detection, the few normal target images provide no direct defect supervision, making anomaly prompts difficult to learn
arXiv:2610.06919v1 Announce Type: new Abstract: This paper concerns how semantic context determines geometry in learned vector representations. Similarity is typically measured using cosine similarity
arXiv:2610.07694v1 Announce Type: new Abstract: The integrative analysis of histopathological Whole-Slide Images (WSIs) and transcriptomic profiles holds significant promise for cancer survival predic
Another PR of ours just merged into llama.cpp: the fast Metal kernels from Monday now cover all 26 weight formats the Mac GPU runs. They made speculative decoding faster on Mac for 10 formats, and thi
Carl Franzen / VentureBeat: Anthropic cuts Sonnet 5.5 cache read price from 0.20 to 0.10 and adds monthly API credits: 100 for Max 5x, 200 for Max 20x, up to 500 shared by Team users — The model start
Anthropic: Anthropic launches Claude Haiku 5.5, the first Haiku model with effort controls, for high-volume, cost-sensitive tasks like summary and classification requests — Introducing Claude Haiku 5.
Frederic Lardinois / The New Stack: Anthropic prices Haiku 5.5 at 0.10/1M input and 0.50/1M output tokens for requests up to 100K tokens, and 0.50 and 2.50 above, vs. 1 and 5 for Haiku 4.5 — Anthropic
Anthropic PBC today released Claude Haiku 5.5, pricing its newest small model at roughly a quarter of what Haiku 4.5 costs to run. Claude Sonnet 5.5 is getting cheaper as well, since the company is ha
arXiv:2610.08552v1 Announce Type: new Abstract: Concept bottleneck models (CBMs) make predictions inspectable and intervenable by routing them through human-interpretable concepts, but originally requ
arXiv:2610.08210v1 Announce Type: cross Abstract: For a given data distribution (X_t)_{t in N} sim Q i.i.d., we investigate the hypothesis testing problem: H_0: Q = P_0 vs. H_1: Q = P_1, for two diffe
arXiv:2610.06966v1 Announce Type: cross Abstract: Indirect prompt injection (IPI) hides adversarial instructions in content that large language model (LLM) agents read at runtime. As agents compose he
arXiv:2610.07780v1 Announce Type: new Abstract: Speculative decoding reduces large language model inference latency by drafting multiple tokens before target-model verification, but its effectiveness
arXiv:2610.07904v1 Announce Type: new Abstract: We introduce ApexQuant, a calibration-free quantization method that recursively re-quantizes the residual error, serving as a refinement layer on top of
arXiv:2610.08037v1 Announce Type: new Abstract: Language models frequently generate outputs in unintended languages or scripts, a phenomenon known as off-target generation. While existing research has
arXiv:2610.07902v1 Announce Type: new Abstract: Cantonese lyric writing requires close alignment between lexical tones and melodic pitch. Existing melody-guided lyric generation methods typically rely
arXiv:2610.08417v1 Announce Type: new Abstract: Recent advances in LipSync generation technology have led to the creation of highly realistic videos, posing severe societal risks. However, existing de
Since its founding in 2004, it’s arguable that no network vendor has made better switches than Arista Networks Inc. That was true then and remains true, as its prowess in this area helped it ride the
arXiv:2610.07031v1 Announce Type: new Abstract: Recent video world models have witnessed the paradigm shift from single-agent to multi-agent involvements, which can reveal more complicated dynamics an
arXiv:2610.07438v1 Announce Type: cross Abstract: Artifact removal routinely precedes the classification of electrodermal activity (EDA), on the assumption that a cleaner signal supports a better deci
arXiv:2510.22954v2 Announce Type: replace Abstract: Language models (LMs) often struggle to generate diverse, human-like creative content, raising concerns about the long-term homogenization of human
As reported in the @WSJ, we have raised a Series B to bring Hermes Agent to new frontiers (and, yes, build a mobile app) Thank you to our investors including @nvidia @M12vc @SamsungNext @robotventures
arXiv:2610.08446v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) have made significant progress in visual understanding, but precise 3D spatial reasoning integrated with physic
arXiv:2610.07292v1 Announce Type: cross Abstract: Missing covariates are frequently encountered in supervised learning problems, and classical methods for estimation using such data use carefully chos
arXiv:2610.07637v1 Announce Type: cross Abstract: Many real-world datasets exhibit unusually large values far more frequently than predicted by Gaussian models. Heavy-tailed distributions capture this
arXiv:2610.07323v1 Announce Type: cross Abstract: Security evaluation of learning-based systems requires more than just testing the system against a fixed collection of attacks. It requires adaptive m
Atlassian Corp. today announced Agentic Multiplayer Protocol, a platform update designed to change how humans and artificial intelligence agents collaborate and get work done using shared context and
arXiv:2610.08400v1 Announce Type: cross Abstract: Large-scale self-supervised pretraining has reshaped modern machine learning, substantially advancing the ability of language and vision models to gen
arXiv:2610.07785v1 Announce Type: new Abstract: A central capability of embodied agents is to accomplish complex objectives through sequences of interdependent tasks. Yet existing visual goal-conditio
arXiv:2607.17669v2 Announce Type: replace Abstract: Drone-based object detection technology has advanced rapidly, becoming increasingly sophisticated and efficient. Recently, research trends have expa
arXiv:2610.08118v1 Announce Type: new Abstract: Covariate-aware time-series foundation models (TSFMs) promise training-free what-if answers for instrumented plants: the change in output that a differe
arXiv:2610.06927v1 Announce Type: cross Abstract: The key-value (KV) cache of autoregressive transformers grows linearly with context length and dominates memory at long context. Most training-free re
arXiv:2610.07459v1 Announce Type: new Abstract: Organizations make claims about their AI agents: a person approves every external email, every action is logged, an evaluation shows the agent is safe t