Knowledge catalogue
A mental model for working with coding agents is that they're blind squirrels running into a maze and bumping into walls. You must place the walls (verifiable constraints) strategically so that they e
Benedict Evans: An overview of macro tech trends: capex explosion, unprecedented surge in chip demand, supply chain bottlenecks, model commoditization, AI automation, and more — Twice a year, I produc
announcing deepagents v0.6, our biggest release yet! it’s all about performance: at the model layer w harness profiles, agent layer w code interpreter, and at scale w streaming and delta channels cont
arXiv:2605.15995v1 Announce Type: cross Abstract: Learning latent representations from complex data is central to modern machine learning, spanning temporal, multimodal, and partially observed systems
arXiv:2506.22440v2 Announce Type: replace-cross Abstract: This paper introduces the Generality-Accuracy-Simplicity (GAS) framework to analyze how large language models (LLMs) are reshaping organizatio
Introducing Agora-1, a multi-agent world model. Multiple participants—human or AI—can now interact inside the same world simulation, all in real-time. Try our playable research preview today, with Ago
LangSmith Engine automates the full agent fix loop — detecting failures, diagnosing causes and drafting PRs. But multi-model enterprises say a neutral observability layer still wins. http://venturebea
arXiv:2605.15831v1 Announce Type: cross Abstract: Autoregressive music generation depends strongly on the audio tokenizer. Existing high-fidelity codecs often use residual multi-codebook quantization,
arXiv:2605.16107v1 Announce Type: new Abstract: Machine-generated texts (MGTs) pose risks such as disinformation and phishing, underscoring the need for reliable detection. Metric-based methods, which
okay maybe it's a good time? We have a small colbert model trained at pplx, it is a continue-training of pplx-embed-0.6b, so native multilingual, just made it open and added a section how to use MaxSi
Tesla Model Y's powered rear seats and trunk are equipped with automatic obstruction detection that causes them to automatically reverse and pop back up if an obstruction is detected during operation,
AI teams shouldn’t have to choose between expensive object storage and painful git workflows. @huggingface Storage is built for model weights, datasets, checkpoints and artifacts: - simple per-TB pric
arXiv:2605.14773v1 Announce Type: cross Abstract: Data selection accelerates training by identifying representative training data while preserving model performance. However, existing methods mainly f
arXiv:2605.15077v1 Announce Type: cross Abstract: Function calling, also known as tool use, is a core capability of modern LLM agents but is typically constrained by synchronous execution semantics. U
arXiv:2605.14227v1 Announce Type: cross Abstract: Accurate disease trajectory prediction is critical for early intervention, resource allocation, and improving long-term outcomes. While electronic hea
Julie Bort / TechCrunch: In a viral X post that parodies the old Mac vs. PC commercials, General Catalyst posted a “VC vs GC” video, with the VC apparently modeled after Marc Andreessen — One of the m
arXiv:2605.14935v1 Announce Type: new Abstract: We present MSCoT, a multi-scale, coarse-to-fine model for test-time human motion synthesis and control. Unlike recent approaches that rely on multiple i
arXiv:2605.14683v1 Announce Type: new Abstract: High-resolution seafloor mapping necessitates stable and precise positioning for underwater robots. This paper introduces a novel mathematical model for
We’re releasing a 30B-A3B reasoning model that reaches gold-medal level across both physics and math Olympiad evaluations: IPhO directly, and IMO/USAMO with test-time self-verification and refinement.
arXiv:2605.13687v1 Announce Type: cross Abstract: We introduce a family of synthetic languages with hierarchical structure -- generated by a broadcast process on trees -- for which the role of context
arXiv:2510.08992v3 Announce Type: replace Abstract: While researchers have made significant progress in enabling large language models (LLMs) to perform multi-step planning, LLMs struggle to ensure th
Dear AI labs, A neverending black and white kanban board modeled after Jira (no offense) is not what we want as the future of work. Give me flexibility. Give me delight. Give me color. Please create t
arXiv:2406.13619v4 Announce Type: replace-cross Abstract: This paper develops a generative model by minimizing the second-order Wasserstein loss (the W_2 loss) through a distribution-dependent ordinar
Model. Harness. Context. The 3 main components of agents. As you build more agents, context increasingly lives AGENTS.md, skills, policies, examples, + generated research files. Context needs its own
arXiv:2304.11193v2 Announce Type: replace-cross Abstract: Predicting the outcomes of robotic actions, often referred to as learning a world model, in complex environments remains a fundamental challen
Russell Brandom / TechCrunch: Adaption, co-founded by ex-Cohere VP of AI research Sara Hooker, unveils AutoScientist, which can automate the research loop behind model training and alignment — For yea
Owen Walker / Financial Times: China's move to block Meta's Manus acquisition challenges the “Singapore washing” model, as major Chinese tech companies build significant Singapore presences — Beijing'
arXiv:2601.22334v2 Announce Type: replace Abstract: Differentially private stochastic gradient descent (DP-SGD) is the gold standard for training machine learning models with formal differential priva
arXiv:2605.11582v1 Announce Type: new Abstract: Large language models (LLMs) have shown remarkable potential in advertising scenarios such as ad creative generation and targeted advertising. However,
arXiv:2605.11964v1 Announce Type: new Abstract: A target-guided proactive dialogue system aims to steer conversations proactively toward pre-defined targets, such as designated keywords or specific to
External content is scanned in parallel by ML classifiers and the BrowseSafe model before agents act on it. File connector data is encrypted in transit and at rest, uploaded files automatically delete
arXiv:2602.02799v2 Announce Type: replace Abstract: Building agents that can perform new skills by composing existing skills is a long-standing goal of AI agent research. Towards this end, we investig
arXiv:2605.12410v1 Announce Type: cross Abstract: We propose and analyze a model-based bootstrap for transition kernels in finite controlled Markov chains (CMCs) with possibly nonstationary or history
arXiv:2503.09051v2 Announce Type: replace Abstract: We propose a novel model-level GNN explanation framework that shifts the explanation target from class-wise rule extraction to rule-based logit reco
New paper: research agenda for secret loyalties Imagine a frontier model that has been trained to covertly advance a specific actor's interests (a nation-state, a CEO, an adversary). @joemkwon argues
PayPal runs 74,000 weekly tasks in Perplexity Enterprise. Teams use it for model validation, channel performance, market trend research, competitive intelligence, and product analysis. Read the custom
TST works in two phases. In phase 1, which covers the first 20-40% of training, the model reads contiguous bags of k tokens, with input embeddings averaged within each bag, and predicts the next bag o
arXiv:2605.09492v1 Announce Type: cross Abstract: Large language models (LLMs) often suffer from hallucinations due to error accumulation in autoregressive decoding, where suboptimal early token choic
arXiv:2605.09579v1 Announce Type: cross Abstract: Cardiovascular disease remains the leading cause of global mortality, yet scalable cardiac monitoring is hindered by the gap between diagnostic-rich E
arXiv:2508.04660v2 Announce Type: replace Abstract: Group Relative Policy Optimization (GRPO) has proven to be an effective tool for post-training language models (LMs). However, AI systems are increa
Delighted to announce our 3rd world modeling workshop! After NYC and Montreal, we are now headed to Chicago! - August 31st to September 2nd - CfP and details on the website: https://wm-booth.org - @yl
arXiv:2512.06673v2 Announce Type: replace Abstract: Multimodal large language models (MLLMs) are rapidly expanding from general video understanding to finer-grained understanding such as spatio-tempor
arXiv:2605.10343v1 Announce Type: cross Abstract: Streaming video understanding demands more than watching longer videos: assistants must decide when to speak in real time, balancing responsiveness ag
arXiv:2509.15519v2 Announce Type: replace Abstract: This paper studies fully decentralized cooperative multi-agent reinforcement learning, where each agent solely observes the states, its local action
arXiv:2510.13896v2 Announce Type: replace-cross Abstract: Cellular image segmentation is essential for quantitative biology yet remains difficult due to heterogeneous modalities, morphological variabi
arXiv:2605.10624v1 Announce Type: new Abstract: Model Predictive Control (MPC) is widely used to operate safety-critical infrastructure by predicting future trajectories and optimizing control actions
arXiv:2605.09994v1 Announce Type: cross Abstract: Modern Large Foundation Model (LFM) training has transformed the data pipeline from a static ingestion layer into a dynamic component that must co-evo
arXiv:2605.08755v1 Announce Type: new Abstract: Large reasoning models (LRMs) reach competition-level math and coding accuracy via long autoregressive decoding, making per-token decoding cost a primar
arXiv:2605.08525v1 Announce Type: new Abstract: We introduce a model-reference adaptive control (MRAC) architecture for high-performance positional tracking of the Bee++, a 95-mg insect-scale flapping
arXiv:2605.08835v1 Announce Type: new Abstract: The expansion of Artificial Intelligence-generated content service requires diffusion model serving to simultaneously achieve high throughput and low ta
Connie Loizos / TechCrunch: The US' Centers for Medicare & Medicaid Services is testing ACCESS, an outcome-based payment model for AI-driven medical care, with 150 tech companies — Neil Batlivala has
arXiv:2605.10020v1 Announce Type: new Abstract: Generating high-fidelity synthetic GPS trajectories is increasingly important for applications in transportation, urban planning, and what-if scenario s
arXiv:2605.07052v1 Announce Type: cross Abstract: We generalize Jan Willems' behavioral approach to a class of discrete-time nonlinear systems in a vector-valued reproducing kernel Hilbert space (RKHS
arXiv:2605.06821v1 Announce Type: cross Abstract: Cohen et al. (arXiv:2207.14484) observed that adaptive gradient methods such as Adam operate at the edge of stability. While there has been significan
arXiv:2605.06879v1 Announce Type: new Abstract: Protein sequence data from nature exhibits survivorship bias: we only observe data from those organisms that survive and reproduce, while non-functional
arXiv:2605.07878v1 Announce Type: new Abstract: Access to modern generative systems is often restricted to querying an API (the ``black-box' setting) and many properties of the system are unknown to t
arXiv:2605.07642v1 Announce Type: new Abstract: Forecasting future 3D hand pose sequences from egocentric video is essential for understanding human intention and enabling embodied applications such a
🆕 Hugging Face 🤝 Hermes Agent 🔥 > we added Hermes Agent to local apps: run it locally with any compatible GGUF/MLX model > shipped native traces support for Hermes Agent: visualize your Hermes traces
arXiv:2605.07082v1 Announce Type: new Abstract: In the design of surgical guides for implant placement, determining the precise implant position is a critical step. However, the implant region itself
arXiv:2602.20974v2 Announce Type: replace Abstract: In engineering design and scientific computing, computational cost and predictive accuracy are intrinsically coupled. High-fidelity simulations prov