Knowledge catalogue
arXiv:2610.16433v1 Announce Type: new Abstract: Time Series Foundation Models (TSFMs) provide general-purpose forecasting capabilities, yet their forecasts can remain misaligned with the temporal char
arXiv:2610.17128v1 Announce Type: new Abstract: Egocentric video provides a continuous first-person record of everyday activities, making it a natural foundation for wearable AI assistants. Unlike off
arXiv:2610.14977v1 Announce Type: new Abstract: Embodied agents built on foundation models rely on an execution harness to organize observations, guide actions, and incorporate execution feedback into
arXiv:2610.14982v1 Announce Type: new Abstract: Recurrent algorithmic reasoners are trained with per-step hints on small graphs and run for many more steps on large ones. On breadth-first search in SA
arXiv:2610.16236v1 Announce Type: new Abstract: Morphogenesis is driven by the interplay of genetic regulation and tissue mechanics. In vivo video data is limited, particularly under genetic mutations
arXiv:2610.16558v1 Announce Type: cross Abstract: World models capture environment dynamics and support counterfactual reasoning for planning. In image-goal navigation, where the target often lies bey
arXiv:2610.15900v1 Announce Type: new Abstract: We present Gen Through the Lens, a camera-controllable image-to-video generation framework that synthesizes videos from a given reference image while en
arXiv:2610.15707v1 Announce Type: new Abstract: A central desideratum in model editing is generalization to complex tasks, which prior work formalizes under a direct generalization paradigm: treating
arXiv:2610.18694v1 Announce Type: new Abstract: Vision-language models (VLMs) struggle with metric and multi-view relationships that remain implicit in RGB observations. Geometry foundation models rec
arXiv:2610.13941v2 Announce Type: replace Abstract: Multimodal diffusion transformers (MMDiTs) allow the evolving image to update internal text representations through joint attention. These represent
arXiv:2610.16502v1 Announce Type: new Abstract: Discovering and disambiguating entities from multimodal and heterogeneous data is a key challenge in discovery science, where relevant knowledge is ofte
arXiv:2610.14448v1 Announce Type: new Abstract: Asynchronous rollout improves the efficiency of reinforcement learning with verifiable rewards (RLVR) by reducing under-utilization during long-tail gen
arXiv:2610.17685v1 Announce Type: cross Abstract: Enterprise agents face safety risks that cannot be determined from individual actions alone. Existing safety benchmarks largely evaluate action-local
arXiv:2610.16299v1 Announce Type: new Abstract: Video anomaly understanding (VAU) aims to generate language-level interpretations of anomalous events in long videos, requiring visual evidence that sup
arXiv:2610.18352v1 Announce Type: new Abstract: A robot following a multi-step instruction needs to act on the right objects in the right order, even as the scene changes. It must also maintain awaren
arXiv:2610.15840v1 Announce Type: new Abstract: Reinforcement learning (RL) for large language model (LLM) agents remains challenging in long-horizon tasks with sparse outcome rewards, where assigning
arXiv:2610.17039v1 Announce Type: cross Abstract: Tool-using LLM agents are increasingly used to automate workflows governed by procedural manuals, such as company rules for booking travel or procurin
arXiv:2508.21044v2 Announce Type: replace Abstract: Video Large Language Models (VLLMs) excel in video understanding, but their excessive visual tokens pose a significant computational challenge for r
arXiv:2610.16135v1 Announce Type: cross Abstract: Omni-modal large language models (Omni-LLMs) extend LLMs to process heterogeneous modalities (e.g., vision, audio, and IMU signals) alongside language
arXiv:2610.14022v1 Announce Type: new Abstract: On-policy distillation (OPD) improves language-model by supervising a student on prefixes sampled from its own policy, but its supervision remains confi
arXiv:2508.12943v3 Announce Type: replace-cross Abstract: Public service systems in many African regions suffer from delayed emergency response and spatial inequity, causing avoidable suffering. This
arXiv:2610.14001v1 Announce Type: new Abstract: On-policy self-distillation (OPSD) uses a self-teacher conditioned on privileged information to turn the sparse outcome signal of reinforcement learning
arXiv:2610.16967v1 Announce Type: new Abstract: Physical AI is commonly formulated around an explicitly specified task: given a goal or instruction, a system perceives, reasons, and acts. In many real
arXiv:2610.16134v1 Announce Type: new Abstract: Dataset distillation (DD) aims to retain the training utility of a large dataset in a much smaller set of examples. For skeleton-based action recognitio
arXiv:2610.14737v1 Announce Type: new Abstract: Training language agents on long-horizon interactive tasks is challenging because sparse terminal rewards provide weak credit signals for intermediate a
arXiv:2610.14635v1 Announce Type: cross Abstract: Large Vision-Language Models (LVLMs) have achieved remarkable progress across a wide range of multimodal tasks. However, object hallucination remains
arXiv:2610.14519v1 Announce Type: new Abstract: Effectively eliciting the capabilities of large language models (LLMs) at inference time remains an important challenge. Existing studies address this c
arXiv:2610.16763v1 Announce Type: new Abstract: Relational learning typically predicts from a database state, but decision making asks a different question: how will that state change under an action?
tl;dr: new qwen finetune that simultaneously pushes the frontiers of small model capability and reasoning efficiency. Hey everyone, We publish two post-trained versions of Qwen 3.8 27B called Sabi-Noe
arXiv:2610.15186v1 Announce Type: cross Abstract: Retrieval-augmented generation (RAG) reuses the same documents across many requests, making non-prefix KV-cache reuse attractive. Yet a cached documen
arXiv:2610.16106v1 Announce Type: new Abstract: Multimodal entity alignment (MMEA) is fundamental to integrating heterogeneous knowledge graphs (KGs), yet existing paradigms remain critically vulnerab
arXiv:2603.02475v2 Announce Type: replace Abstract: Skin tone classification is a fundamental task in computer vision, with applications in quantifying medical features, assessing demographic represen
arXiv:2610.14671v1 Announce Type: new Abstract: Streaming video understanding requires answering questions from the observed video, with evidence drawn from recent observations or earlier events. Hist
arXiv:2610.17692v1 Announce Type: new Abstract: 3D scene graph prediction is commonly optimized with object-node and relation-edge classification losses. These objectives encourage exact object and re
arXiv:2610.14663v1 Announce Type: new Abstract: 4D Gaussian Splatting (4DGS) has emerged as a powerful dynamic scene representation, supporting real-time high quality rendering but suffers from prohib
arXiv:2610.14944v1 Announce Type: new Abstract: Specifying segmentation targets with natural language provides flexible semantic conditioning for medical image segmentation. However, existing methods
arXiv:2610.16565v1 Announce Type: new Abstract: Human gaze is the primary high-bandwidth interface through which we parse the semantics of our environment. While often modeled as a sequence, the degre
arXiv:2610.16969v1 Announce Type: cross Abstract: Latent Action Models (LAMs) can capture manipulation priors from action-free videos, but discrete latents usually impose a granularity bottleneck, lim
arXiv:2610.17057v1 Announce Type: cross Abstract: Vision-based document retrieval has improved rapidly, but current evaluation settings still emphasize short documents and single relevant pages. This
arXiv:2610.14958v1 Announce Type: cross Abstract: Activation steering has recently been used as a memory for skills: past experiences of an agent are stored as steering vectors and retrieved later. Fa
arXiv:2610.14009v1 Announce Type: new Abstract: Large AI models increasingly rely on distributed GPU execution, yet it remains unclear whether established failure analysis methods transfer effectively
arXiv:2610.15929v1 Announce Type: new Abstract: Recent trackers built on foundation models such as the Segment Anything Model (SAM) achieve strong performance by propagating object masks through memor
arXiv:2610.18067v1 Announce Type: cross Abstract: Scaling interactive environments is important for training long-horizon agents through reinforcement learning. These environments often require furthe
Brilliant paper on agentic continual learning from Meta and MIT. (bookmark it) Agent memory harnesses usually only write forward. A lesson goes into the bank and is never checked against whether it he
@cjav_dev @aiDotEngineer @ricmac @latentspacepod our workshop writeup is live now! https://x.com/latentspacepod/status/2109713951604826153?s=20 At AI Engineer New York, Anthropic's @cjav_dev & @Harris
The reality for most organizations is that data lives everywhere. As engineering teams expand and adopt specialized platforms for their workloads, enterprise data naturally disperses across multiple c
David Silver is one of the all-time greats. He was the creator of AlphaGo, which changed the course of history by showing that neural nets could achieve superhuman performance for the first time. He a
Last week we announced that Gemini Enterprise has evolved to make it even simpler to get work done, and introduced the Gemini agent, your new universal agent for work. It's always on and ready to answ
If an agent saves an engineer 2 hours to implement a feature but collectively costs the team 3 hours in alignment and review, the ROI is negative. Isolated chats are suboptimal in team environments be
Quartermaster (my local inference manager: one server that swaps llama.cpp, image, audio and video models in and out of VRAM) can now help you server and manage decision models: Auto-discovered. Drop
Hi, I see that vllm released d3 (a family of decision models) and llama.cpp already has support for them. I want to try them out. Are decision models sensitive to quantization? I know that for autocom
Enterprise management software company Workday Inc. today announced that it wants to turn its existing knowledge of people, money and business rules into an operational foundation for agentic artifici
arXiv:2610.13627v1 Announce Type: new Abstract: Evaluating large language models (LLMs) on AMLworld's smallest test splits is costly because each of over a million targets requires a separate graph pr
arXiv:2610.12496v1 Announce Type: cross Abstract: Sequence models with a fixed-size state avoid the quadratic cost of attention, but face a design choice. An input-dependent state transition gives con
llama : report compute graph reallocations during inference (#30329) Add an optional ggml_backend_sched_realloc_callback that user code registers with ggml_backend_sched_set_realloc_callback to be not
arXiv:2610.12527v1 Announce Type: new Abstract: Distribution operators need visibility of behind-the-meter photovoltaic (PV) generation, yet most residential customers are observed only through net sm
arXiv:2610.13277v1 Announce Type: cross Abstract: Memory-augmented assistants retrieve evidence from stored conversations and documents to answer queries. Most embedding-based retrievers compare singl
arXiv:2610.12872v1 Announce Type: new Abstract: Large language models (LLMs) demonstrate strong individual task performance, yet still struggle to collaborate with users over extended, multi-turn inte
arXiv:2610.13113v1 Announce Type: cross Abstract: Continual post-training faces a dual challenge of acquisition and retention: models must learn new capabilities while preserving prior knowledge. Whil
arXiv:2507.19608v2 Announce Type: replace Abstract: On-device LLM inference is increasingly important for edge platforms but remains challenging due to high computational and memory demands and tight