Knowledge catalogue
The memory ownership point is the real story here. Running a persistent agent 24/7, memory isn't a feature — it's the entire value layer. Lose it and you're back to day zero. Open harness + portable m
arXiv:2610.13407v1 Announce Type: new Abstract: Exhaustive optimistic scoring can make action selection costly in linear bandits with a large fixed set of K actions, requiring O(K) score evaluations p
arXiv:2610.11552v1 Announce Type: new Abstract: Large language model agents can invoke tools fluently, but enterprise workflows demand more than selecting the right tools: actions must strictly comply
arXiv:2610.06257v1 Announce Type: new Abstract: Foundation models can generate scientific code, but authoring a scientific simulator (an executable program encoding hypotheses about how mechanisms gen
arXiv:2610.06002v1 Announce Type: cross Abstract: Diffusion models provide expressive priors over trajectories, but adapting these priors to test-time constraints requires maintaining feasibility and
arXiv:2610.01097v1 Announce Type: new Abstract: End-to-end research agents can now produce complete scientific papers, yet manuscript claims often diverge from executed experiments. This gap is struct
arXiv:2610.00722v1 Announce Type: new Abstract: World models enable agents to plan by predicting future states of the environment, but their predictions can become unreliable when test-time dynamics d
arXiv:2610.01165v1 Announce Type: new Abstract: Layer interventions are widely used to probe the internal organization of language models, yet most analyses examine a single training checkpoint even t
Row-Bot 5.0 is a major rebuild of the local-first AI assistant. The NiceGUI interface is gone, replaced by one React app across desktop, browsers, phones and tablets. The biggest change is how work is
arXiv:2609.39024v1 Announce Type: new Abstract: Text-to-image (T2I) generation is gaining increasing popularity with the general public, motivating the development of reliable mechanisms for copyright
Behavior intelligence company Exabeam Inc. today introduced a batch of new artificial intelligence features that push its cloud-based New-Scale platform further into agent-driven investigations. The c
arXiv:2609.40118v1 Announce Type: new Abstract: As LLM capabilities advance, agents are tackling increasingly complex tasks over longer horizons. Their growing interaction histories make memory compac
arXiv:2609.39976v1 Announce Type: cross Abstract: Mobile terminals need to provide application and network services while supporting users' control over their attention. We explore voice-first interac
arXiv:2609.38353v1 Announce Type: cross Abstract: Long-term memory lets LLM agents recall past interactions and remain consistent across sessions, but memory systems are hard to compare because they o
arXiv:2609.34994v1 Announce Type: cross Abstract: Most music-generation systems are still framed and evaluated primarily as producers of complete outputs, whereas composition often proceeds through su
arXiv:2609.33258v1 Announce Type: cross Abstract: Recent task-driven and just-in-time 3D Scene Graph (3DSG) methods reduce per-task representations by constructing or activating only task-relevant inf
arXiv:2609.22858v1 Announce Type: new Abstract: World models allow robots to anticipate action consequences before execution. This capability is especially valuable in excavation, where each scoop res
arXiv:2609.21621v1 Announce Type: new Abstract: Fine-grained object (FO) manipulation requires robots to distinguish a specified FO from visually similar objects and execute actions reliably despite s
arXiv:2606.18960v3 Announce Type: replace Abstract: Action-conditioned world models have emerged as a promising paradigm for robot learning, offering a scalable alternative to costly real-world experi
arXiv:2609.17326v1 Announce Type: new Abstract: Scientific poster generation distills a multimodal paper into a single-page visual artifact, forcing strict trade-offs between informational coverage an
arXiv:2609.04773v1 Announce Type: cross Abstract: Distillation is common in LLM post-training, where on-policy knowledge distillation (OPKD) uses student-generated trajectories to prepare the student
arXiv:2609.04869v1 Announce Type: new Abstract: Computer-use agents can execute increasingly complex tasks in graphical interfaces, but their interaction experience is typically transient: procedural
arXiv:2609.02129v1 Announce Type: new Abstract: Data-centric agents repeatedly perform a discovery step before planning or execution: identifying the data objects relevant to a task. Yet successful di
arXiv:2609.00546v1 Announce Type: cross Abstract: Agent systems are commonly described by the model and harness that currently produce their behavior. That boundary is useful for one execution but und
arXiv:2609.00342v1 Announce Type: new Abstract: Whole-slide images (WSIs) are challenging for vision-language reasoning because diagnostically relevant morphology is sparse, heterogeneous, and distrib
arXiv:2608.27454v1 Announce Type: new Abstract: Agent skills package specialized knowledge and workflows into reusable resources that extend AI agent capabilities. Recent work automatically discovers
arXiv:2608.23383v1 Announce Type: new Abstract: Video generation is progressing beyond isolated clips toward long-form narratives and interactive worlds, requiring models to preserve identities, follo
arXiv:2608.21422v1 Announce Type: new Abstract: CBCT (Cone Beam Computed Tomography) scans provide detailed three-dimensional images, widely used in dentistry for diagnostic and treatment planning tas
arXiv:2608.21676v1 Announce Type: new Abstract: Robotic systems are traditionally designed and deployed in static configurations, with assumptions made at design-time becoming immutable constraints du
arXiv:2608.21867v1 Announce Type: new Abstract: LLM agents are moving from single-prompt use to long task streams in which reusable memory becomes a core capability for terminal, software-engineering,
arXiv:2603.02229v2 Announce Type: replace-cross Abstract: Safety post-training has been studied extensively in single-step 'chat' settings where safety typically refers to refusing harmful requests. W
arXiv:2608.12864v1 Announce Type: cross Abstract: Public blockchain data enables large-scale DeFi-related analysis, but many existing approaches are application-specific, difficult to scale, or hard t
arXiv:2608.08910v1 Announce Type: new Abstract: PTQTP decomposes LLM weight matrices into two ternary (trit) planes with two free per-group scales. Tying the scales to a fixed ratio of three collapses
arXiv:2608.06729v1 Announce Type: cross Abstract: While Vision-Language-Action (VLA) models have advanced embodied AI, their fundamentally reactive paradigm severely limits performance in partially ob
If you run local agentic coding harnesses (Aider, Claude Code, etc.), prompt evaluation usually eats up most of your execution time. Every turn re-evaluates thousands of identical prefix tokens_system
arXiv:2607.21547v1 Announce Type: new Abstract: The rapid progress of AI has intensified the long-standing pursuit of automation: replacing human participation with algorithms wherever possible. Impli
arXiv:2607.19708v1 Announce Type: new Abstract: Fully actuated unmanned aerial vehicles (UAVs) are usually certified through rank conditions on a control-allocation matrix or through free-flight track
arXiv:2603.03482v2 Announce Type: replace-cross Abstract: Interactive world models continually generate video by responding to a user's actions, enabling open-ended generation capabilities. However, e
arXiv:2601.22601v2 Announce Type: replace Abstract: Federated unlearning (FU) aims to erase designated client-level, class-level, or sample-level knowledge from a global model. Existing studies common
arXiv:2605.28201v1 Announce Type: new Abstract: Large Language Model (LLM) agents remain vulnerable to safety threats from the external environment, where attackers inject adversarial content into ext
arXiv:2401.01160v3 Announce Type: replace-cross Abstract: We investigate a framework for train-free MRI segmentation based on Topological Data Analysis. The pipeline proceeds in three steps, first ide
arXiv:2605.17478v1 Announce Type: new Abstract: Visual Geometry Grounded Transformers (VGGT) have set new benchmarks in high-fidelity 3D scene reconstruction. However, as the sequence length increases
arXiv:2510.15995v3 Announce Type: replace-cross Abstract: We study overpricing in a repeated game between two representative agents: a market maker, who controls market liquidity, and a market taker,
arXiv:2602.16360v2 Announce Type: replace Abstract: Our understanding of the oceans remains limited by sparse and infrequent observations, primarily because current methods are constrained by the high
arXiv:2605.00814v1 Announce Type: new Abstract: While autoregressive Large Vision-Language Models (LVLMs) demonstrate remarkable proficiency in multimodal tasks, they face a 'Visual Signal Dilution' p
arXiv:2508.13650v3 Announce Type: replace Abstract: As large language models (LLMs) are increasingly deployed in real-world applications, the need to selectively remove unwanted knowledge while preser
arXiv:2604.22778v1 Announce Type: cross Abstract: We present the first systematic study of weight matrix singular value spectra during transformer pretraining, tracking full SVD decompositions of ever
arXiv:2505.20435v3 Announce Type: replace-cross Abstract: Existing interpretability methods for Large Language Models (LLMs) predominantly capture linear directions or isolated features. This overlook
arXiv:2603.27312v2 Announce Type: replace Abstract: Maximum entropy (MaxEnt) modelling provides a principled framework for generating synthetic populations from aggregate census data, without access t
arXiv:2609.36373v1 Announce Type: cross Abstract: A personal language agent that acts for its owner across private and shared conversations can learn a fact from one audience and later place it in the
arXiv:2609.37836v1 Announce Type: new Abstract: Neural networks trained toward the same final objective can reach similar predictive performance while retaining internal representations shaped by earl
arXiv:2609.32965v2 Announce Type: replace Abstract: Multiple agents may often conflict in an organization: for example, one coding agent changes an interface in a repository, but another continues to
arXiv:2609.36843v1 Announce Type: new Abstract: Interpretability methods such as probes, activation patches and learned editors are designed to reveal or modify a model's current computation. World mo
arXiv:2609.27342v1 Announce Type: new Abstract: Cutting changes both the shape and topology of deformable objects, making accurate simulation challenging for robotic manipulation. A simulator must tra
arXiv:2609.27677v1 Announce Type: new Abstract: Fixed roadside cameras repeatedly observe a stable scene overlaid by sparse moving traffic. Temporal memory can recover weak observations, but reusing m
arXiv:2609.10413v1 Announce Type: new Abstract: Current LLM memory systems treat all personal facts identically, so stores grow without bound while retrieval precision degrades. The core challenge is
arXiv:2609.06934v1 Announce Type: new Abstract: Post-hoc safety training (RLHF, DPO) is the dominant way to align large language models, yet jailbreaks (Zou et al., 2023b), fine-tuning attacks (Qi et
arXiv:2608.23650v1 Announce Type: new Abstract: The perception of 3D space by mobile robots is rapidly moving from flat metric grid representations to hybrid metric-semantic graphs built from human-in
arXiv:2608.24764v1 Announce Type: new Abstract: Large language model agents are moving beyond conventional retrieval-augmented generation toward direct interaction with external corpora. Direct Corpus
Nvidia Corp. reported better-than-expected second-quarter earnings and revenue and also delivered bullish guidance for the current quarter and next full year, sending its stock up more than 4% in afte