Knowledge catalogue
arXiv:2610.04517v1 Announce Type: cross Abstract: Deep time-series forecasting models have rapidly diversified, yet adapting them to a specific task still requires extensive expert effort in model sel
arXiv:2610.05418v1 Announce Type: cross Abstract: Most vision-language-action (VLA) models rely on current observations and lose task-relevant evidence once it leaves view, limiting performance on lon
arXiv:2606.16184v2 Announce Type: replace Abstract: Multi-shot long-form video generation remains challenging due to identity drift and compounding inconsistencies across shots. Existing methods encod
arXiv:2610.05639v1 Announce Type: new Abstract: Autonomous robots operating over long periods must keep their environmental memory up to date as the world changes between visits. In semi-static enviro
arXiv:2610.06621v1 Announce Type: new Abstract: Spectral variants of low-rank adaptation (LoRA) choose both a subspace and which factor to freeze. We separate these choices by freezing the input facto
arXiv:2610.04585v1 Announce Type: new Abstract: Joint-embedding predictive architectures (JEPAs) for world modeling train an encoder so a predictor maps a current embedding and action to the next fram
arXiv:2610.05139v1 Announce Type: new Abstract: Code large language model (Code LLM) assistants generate code from heterogeneous development contexts, including open files, imported modules, pasted sn
arXiv:2610.05135v1 Announce Type: new Abstract: Under a fixed physical law, the visible geometry of a scene determines how motion must change. We ask how video generators realize this relationship. We
arXiv:2605.06350v2 Announce Type: replace Abstract: LLM cascades, in which a cheap model defers to an expensive one on low-confidence queries, are widely used to reduce inference cost. Given a pool of
arXiv:2610.04703v1 Announce Type: cross Abstract: Recently proposed Drifting Models shift iterative distribution refinement from inference to training, enabling effective one-step generation. However,
arXiv:2610.04510v1 Announce Type: cross Abstract: Diffusion models for structured scientific generation must produce samples satisfying hard geometric constraints imposed by physics, chemistry, or bio
I’ve been building this for a long fucking time, and tonight I finally released Memoria 1.0.0. I built it because I actually wanted to use it. I wanted a real memory layer for local LLM applications t
arXiv:2610.05277v1 Announce Type: cross Abstract: Code language models must be maintained like the software around them: when a library evolves, a model keeps writing the interface that it saw during
arXiv:2610.06210v1 Announce Type: new Abstract: Autoregressive generation is natural for language, where predicted tokens can be directly reused as the next prediction state, but trajectory forecastin
arXiv:2610.06378v1 Announce Type: new Abstract: The rapid evolution of video generation has narrowed the perceptual gap between authentic and synthetic videos, making generalizable AI-generated video
arXiv:2512.15621v2 Announce Type: replace Abstract: Occupancy world models use historical occupancy states to forecast future 3D scenes, but their robustness under corrupted temporal inputs remains po
arXiv:2610.04916v1 Announce Type: new Abstract: Urban navigation requires embodied agents to pursue long-horizon goals through local decisions based on egocentric observations. However, existing agent
arXiv:2606.16496v2 Announce Type: replace-cross Abstract: Large multimodal language models (MLLMs) have emerged as powerful tools for guiding evolutionary search toward interpretable programmatic poli
arXiv:2610.04778v1 Announce Type: new Abstract: Patient world models are increasingly proposed for longitudinal prediction, intervention-aware reasoning, and clinical-trial simulation. Causal or clini
arXiv:2610.05833v1 Announce Type: cross Abstract: Long-running agents repeatedly call an LLM while retaining most of their document window, evicting old documents, and appending new ones. These rollin
arXiv:2610.04929v1 Announce Type: new Abstract: Robot agents must connect their intended actions to observed outcomes while retaining the context needed to revise their choices over repeated attempts.
arXiv:2610.05371v1 Announce Type: new Abstract: Ensemble guidance combines pretrained diffusion priors with black-box forward models to solve inverse problems without differentiating through the physi
arXiv:2610.05131v1 Announce Type: new Abstract: Intermediate-layer features from multimodal large language models have shown strong potential for video anomaly detection (VAD), yet the origin of their
arXiv:2610.04250v1 Announce Type: new Abstract: Reinforcement learning for embodied control remains constrained by the difficulty of reward specification. Although recent large language model (LLM)-ba
arXiv:2610.05715v1 Announce Type: new Abstract: Vision-language models (VLMs) can detect that an object has rotated across views, but cannot reliably tell by how much. We introduce OR-Bench, a fine-gr
arXiv:2610.06795v1 Announce Type: new Abstract: We introduce Round-Trip KNN Clustering (RTKNNC), a graph-based method for finding cluster structure at several neighbourhood scales without requiring th
arXiv:2610.04109v1 Announce Type: new Abstract: Real-world time series are frequently driven by exogenous events and structural shifts, rendering conventional forecasting based solely on historical nu
arXiv:2610.05831v1 Announce Type: new Abstract: Terminal agents are commonly trained by imitating long teacher trajectories, yet how much of each trajectory to supervise remains unexplored. We study t
arXiv:2508.01802v2 Announce Type: replace Abstract: Soccer analytics draws on two kinds of information: spatio-temporal data describing where players and the ball are, and event data describing what t
arXiv:2610.06814v1 Announce Type: new Abstract: World models learn to predict how their environment will evolve, making them an important foundation for general-purpose robotic control. Yet world acti
arXiv:2610.04701v1 Announce Type: new Abstract: Memory is essential for long-horizon robotic manipulation, where successful actions may depend on past events that are no longer recoverable from the cu
arXiv:2602.20297v2 Announce Type: replace-cross Abstract: We study gap-dependent regret for reinforcement learning with linear function approximation. While prior works have established gap-dependent
AI agent memory is creating new demands on infrastructure as agents run longer sessions and spread across the enterprise. Retaining that context and making it available when needed puts pressure on me
arXiv:2610.02711v1 Announce Type: cross Abstract: Human activity recognition (HAR) from wrist-worn accelerometers is increasingly used for health and behavioral tracking. Yet, most wearable HAR models
arXiv:2610.02753v1 Announce Type: cross Abstract: The practical success of conditional image generation hinges on fine-grained differences in condition alignment and visual fidelity. Classifier-free g
arXiv:2506.10944v2 Announce Type: replace-cross Abstract: Understanding and controlling the atomistic-level reactions governing the formation of the solid-electrolyte interphase (SEI) is crucial for t
arXiv:2610.02914v1 Announce Type: new Abstract: Autoregressive video models can generate minute-long videos in real time, but they produce generic subjects from text rather than specific subjects from
arXiv:2610.02844v1 Announce Type: new Abstract: Ensuring the safe and reliable deployment of large language models (LLMs) remains a fundamental challenge. Existing safety alignment approaches either i
arXiv:2610.02265v1 Announce Type: cross Abstract: Neural video codecs derive motion and temporal contexts mainly from RGB frames, leaving room for cross-modal guidance from complementary temporal obse
arXiv:2610.03374v1 Announce Type: new Abstract: Embodied world models enable scalable simulation of embodied interactions for robot learning. However, existing models are prone to Model Laziness, as t
arXiv:2610.03123v1 Announce Type: cross Abstract: Existing streaming vision-language models (VLMs) continuously perceive and reason over visual streams, but their computational pathways remain fixed t
arXiv:2610.02697v1 Announce Type: cross Abstract: Recent vision-and-language navigation (VLN) systems increasingly adopt streaming Video-LLM policies that map egocentric RGB observations and instructi
arXiv:2610.03574v1 Announce Type: new Abstract: We introduce HyperBrowseComp, a multilingual and multimodal browsing benchmark comprising 423 manually authored and human-validated questions across 13
arXiv:2610.02815v1 Announce Type: new Abstract: Long chain-of-thought reasoning substantially increases KV-cache memory during autoregressive decoding, as every generated token introduces new key and
arXiv:2610.02684v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly explored for clinical reasoning, but whether they appropriately revise judgments as patient evidence evolv
arXiv:2610.02525v1 Announce Type: new Abstract: Long-horizon research agents must decide both how to investigate and what to investigate next as evidence accumulates. This is hard to learn because suc
arXiv:2602.03255v2 Announce Type: replace Abstract: Computer-use agents (CUAs) execute multi-stage tasks through tools, where an early unsafe decision can propagate to consequential actions. Evaluatin
arXiv:2610.03093v1 Announce Type: new Abstract: Standard autoregressive (AR) models process high-level task instructions, state history, and transient tokens within a single shared sequence of tokens.
arXiv:2610.02902v1 Announce Type: new Abstract: Current analyses of LLMs' parametric knowledge are largely output-centric, drawing conclusions about what a model knows without verifying what it was ac
arXiv:2610.02824v1 Announce Type: new Abstract: Rubric-based reinforcement learning extends reward-driven optimization to open-ended tasks by assigning partial credit to individual response requiremen
arXiv:2610.03001v1 Announce Type: new Abstract: Extracellular electrophysiology records a different set of neurons in every session. Neural foundation models embed each neuron and each session into th
arXiv:2610.03423v1 Announce Type: new Abstract: Reinforcement learning (RL) for Text-to-3D (T23D) generation requires optimization across multiple quality dimensions such as semantic alignment and tex
arXiv:2610.02793v1 Announce Type: new Abstract: Research on LLMs continually uncovers model limitations, their causes, and potential solutions. Yet these human discoveries remain largely disconnected
arXiv:2610.02683v1 Announce Type: new Abstract: Can programmable radio propagation serve as computational depth rather than only as a communication channel or one-shot analog transform? We introduce t
arXiv:2610.02717v1 Announce Type: new Abstract: A key challenge in bringing embodied intelligence into the real world is transferring capabilities from simulation to reality and enabling agents to con
arXiv:2610.02361v1 Announce Type: cross Abstract: Large language model (LLM)-driven evolutionary search is a powerful paradigm for automated program and algorithm discovery, yet existing systems are l
arXiv:2610.02383v1 Announce Type: cross Abstract: Looped Transformers apply the same layers several times per token, adding compute to improve quality without more parameters. Each recursion, however,
arXiv:2610.02839v1 Announce Type: cross Abstract: We show that the causality of language models (LMs) may not be necessary nor optimal. This is the case when system behavior (denoted as S) is incorpor
arXiv:2610.02769v1 Announce Type: cross Abstract: Language agents should draw on prior attempts and environmental feedback to improve subsequent decisions within the same task. However, providing addi
arXiv:2610.02331v1 Announce Type: new Abstract: Interactive world models are increasingly capable of generating environments and acting within them, yet deliberately editing an existing executable wor