Knowledge catalogue
arXiv:2609.08209v1 Announce Type: new Abstract: Learning from Observation (LfO) is a fundamental robotic capability that replicates how humans and animals socially learn from each other. Beyond its bi
arXiv:2606.17886v3 Announce Type: replace Abstract: Monotonicity has been a long-running architectural inductive bias for neural networks, motivated by tabular, scientific, and economic settings where
arXiv:2609.08696v1 Announce Type: cross Abstract: Organoids are three-dimensional tissue models whose morphology provides important insights into tumor development, disease progression, and drug testi
arXiv:2609.07666v1 Announce Type: new Abstract: Full-parameter fine-tuning of large language models has substantial memory costs because backpropagation stores activations and gradients. Zeroth-order
arXiv:2609.06356v1 Announce Type: new Abstract: U-Net remains a practical baseline for image segmentation because of its simple encoder-decoder structure and skip connections. However, the bottleneck
arXiv:2602.01176v2 Announce Type: replace Abstract: Physics-informed neural networks (PINNs) have emerged as a powerful paradigm for solving partial differential equations (PDEs) by embedding physical
arXiv:2609.05574v1 Announce Type: new Abstract: Hypergraph representation learning aims to capture high-order information in graphs by constructing hyperedges that simultaneously connect multiple node
arXiv:2609.06373v1 Announce Type: new Abstract: Generating long-form multi-shot videos requires coherent within-shot motion and visually consistent narratives across shots. Existing video generators f
arXiv:2609.06774v1 Announce Type: cross Abstract: Near-Earth Objects (NEOs) can appear as faint streaks in long-exposure astronomical images. Detecting these streaks across diverse observatories requi
arXiv:2606.19706v2 Announce Type: replace Abstract: Recent progress in vision-language models has enabled processing of increasingly long video sequences, but handling extended token streams does not
arXiv:2609.07009v1 Announce Type: cross Abstract: Multimodal continual learning has recently shown great potential for developing agents with human-like intelligence by continuously learning new tasks
arXiv:2604.03353v2 Announce Type: replace-cross Abstract: While neural lossless image compression has advanced significantly with learned entropy models, lossless video compression remains largely une
Nice paper to improve inference efficiency. It's been a while we haven't seen good work on efficiency. Here is why it matters: A long-running agent's workspace outgrows its context window long before
arXiv:2609.07566v1 Announce Type: new Abstract: Caching systems often rely on simple eviction policies such as Least Recently Used (LRU) and Least Frequently Used (LFU), which perform well in compleme
arXiv:2609.05436v1 Announce Type: cross Abstract: Protein scaffold gap filling is an important computational task in protein sequence reconstruction, where missing amino acid regions must be inferred
arXiv:2609.06876v1 Announce Type: new Abstract: Endovascular procedures rely on real-time manipulation of thin instruments, catheters and guidewires, under X-ray fluoroscopy guidance, where accurate v
arXiv:2609.07135v1 Announce Type: new Abstract: An embodied kitchen assistant must do more than recognize food in isolated frames. It must track ingredient states over time and integrate visual observ
arXiv:2504.15758v3 Announce Type: replace Abstract: We operate through the lens of ordinary differential equations and control theory to study the concept of observability in the context of neural sta
arXiv:2609.08130v1 Announce Type: new Abstract: Driver alerting from dashcam video requires sequential decision-making under partial observability: a system must decide not only whether a scene is ris
arXiv:2606.14199v2 Announce Type: replace-cross Abstract: Large language models are increasingly deployed as human simulators for interactive evaluation and social simulation. Yet helpfulness-driven p
arXiv:2609.05966v1 Announce Type: new Abstract: Existing unlearning approaches typically rely on post hoc weight adaptation or distillation, leading to duplicated memory costs, degraded generalization
arXiv:2609.07681v1 Announce Type: new Abstract: Associative Recall (AR) is the cognitive ability to learn and retrieve links between items in memory. In NLP, AR is used as a benchmark for evaluating t
arXiv:2609.08947v1 Announce Type: cross Abstract: Graph-based surrogate models offer a promising route to accelerate computational fluid dynamics (CFD) simulations on unstructured meshes. However, the
arXiv:2609.05885v1 Announce Type: new Abstract: Low-rank adaptation (LoRA) has become the standard for parameter-efficient fine-tuning of large language models. Most LoRA variants follow a uniform-LR
arXiv:2609.06338v1 Announce Type: new Abstract: Accelerated MRI reconstruction recovers images from undersampled k-space. However, different acceleration factors produce distinct artifact patterns. Ex
arXiv:2609.08276v1 Announce Type: cross Abstract: Handwritten signature verification is vital for personal authentication across commercial and financial applications. Although deep learning methods a
arXiv:2609.06870v1 Announce Type: new Abstract: Visual perception of built environments contributes to the affective impressions that people form in everyday life. However, how these impressions are r
arXiv:2609.06424v1 Announce Type: new Abstract: Homes change between a robot's visits. Navigation benchmarks pose their goals in the world the agent currently sees, and the two-visit benchmarks that e
arXiv:2609.07516v1 Announce Type: new Abstract: Target-based LiDAR-camera extrinsic calibration is a prerequisite for multi-sensor fusion in robotics. However, in the widely adopted four-hole pipeline
arXiv:2609.08740v1 Announce Type: new Abstract: In this paper we derive a Probably Approximately Correct (PAC)-Bayesian error bound for partially observed linear time-invariant (LTI) stochastic dynami
arXiv:2609.07236v1 Announce Type: new Abstract: Selecting a parallelism strategy - the configuration of data, tensor, and pipeline parallelism degrees together with micro- and global-batch sizes - lar
arXiv:2602.05896v3 Announce Type: replace Abstract: Understanding what neural architectures can and cannot compute is a central challenge in the theory of AI. One of the fundamental problems in this c
arXiv:2601.20845v2 Announce Type: replace Abstract: Time series forecasting is a fundamental problem with applications in climate, energy, healthcare, and finance. Many existing approaches require dom
arXiv:2609.06080v1 Announce Type: new Abstract: Deeply phenotyped cohorts combine clinical, imaging, molecular, and wearable observations across timescales from seconds to years. This breadth can reve
arXiv:2609.05808v1 Announce Type: cross Abstract: In situ adjoint training extracts parameter gradients directly from measurement, but has so far been limited to reciprocal or restricted systems. Here
arXiv:2609.08992v1 Announce Type: new Abstract: False ventricular tachycardia (VT) alarms are a leading contributor to alarm fatigue in intensive care units. We propose a deep learning framework combi
arXiv:2507.15824v2 Announce Type: replace Abstract: Text-to-video (T2V) models now produce striking visuals, yet they routinely violate everyday physics; objects float, tools are misused, and causal s
arXiv:2609.06207v1 Announce Type: new Abstract: Image-to-video generators are often credited with absorbing physical dynamics as implicit world models, a claim the community currently checks with plau
arXiv:2609.07762v1 Announce Type: cross Abstract: Recurrent detectors such as bidirectional long short-term memory (Bi-LSTM) networks are low-complexity alternatives to the optimal Bahl-Cocke-Jelinek-
arXiv:2609.08949v1 Announce Type: new Abstract: Object 6D pose estimation formulations have progressively reduced reliance on object-specific priors, evolving from explicit 3D models to multi-view obj
arXiv:2609.06102v1 Announce Type: cross Abstract: Cellular automata is a local computation paradigm where complex behavior can arise from local interactions between simple functions. This paradigm has
arXiv:2609.07199v1 Announce Type: new Abstract: Trust-Hub reuses host circuits: several files differ mainly in the inserted Trojan. When gates from sibling variants enter both training and test folds,
arXiv:2609.05952v1 Announce Type: new Abstract: Nearest-neighbor classification is widely used in machine learning, yet existing methods often suffer from low computational efficiency and limited robu
Qodo has released the Agentic Toolbox, enabling Claude Code, Codex, Kiro, and Cursor to directly utilize QodoAI’s review engine, codebase knowledge base, and team‑specific rules. The launch was announ
I’ve been using Qwen a lot recently and I’m honestly very impressed with it. For some of my tasks, Qwen seems to understand what I’m actually trying to achieve better than ChatGPT/GPT-5.6. I currently
Its chat template has this line: {%- set resolved_reasoning_effort = reasoning_effort|default('xhigh') %} xhigh is the most expensive of its three settings (low / medium / xhigh). If you never set one
Model available here: Qwen3.8-27B-Uncensored-Genesis-V1-MTP-GGUF This model is a practical realisation of things described in this paper, but adapted by me for machine learning: https://arxiv.org/pdf/
Hi, I'm the co-creator of this Qwen3.8-Flash-Next engine support in MLX-serve. I've been tuning this one to run both fast, efficient and correct up 1m context using kv cache 8 bits in M5 Max 128GB. Qw
arXiv:2609.05770v1 Announce Type: new Abstract: Differentially private (DP) fine-tuning methods treat sparse Mixture-of-Experts (MoE) models as a single dense block, ignoring that shared layers see al
arXiv:2609.07547v1 Announce Type: new Abstract: Multi-object tracking (MOT) has advanced rapidly in urban surveillance and autonomous driving, yet many trackers rely on ReID- and transformer-based app
arXiv:2609.06581v1 Announce Type: new Abstract: Small-object detection remains challenging because limited pixels cause information loss and suppress the scale knowledge encoded in pretrained detector
The short film *Love, Rendered* demonstrates how filmmakers partnered with Google DeepMind to use AI‐generated imagery to reconstruct a 70‑year love story that had never been captured on video. Employ
arXiv:2508.11431v3 Announce Type: replace Abstract: An object can disappear from a 3D scene, yet still be detectable. Even after visual removal, modern vision models may infer what was originally pres
arXiv:2609.05438v1 Announce Type: cross Abstract: The human brain folds in utero, primarily during late gestation. Shortly after birth, cortical folding patterns are established and remain stable ther
arXiv:2511.14218v2 Announce Type: replace Abstract: Weather forecast uncertainty arises from imperfect analyses and forecast models, but ensemble spread alone does not reveal how distinct sources rela
arXiv:2609.09069v1 Announce Type: cross Abstract: Autonomous 3D active mapping requires a space robot to choose where to sense while building the geometry needed for navigation. Learned occupancy comp
arXiv:2609.05933v1 Announce Type: new Abstract: Efficiency is increasingly important for Large Language Model (LLM)-based multi-agent systems (MAS), as larger models and more agents introduce substant
arXiv:2609.08090v1 Announce Type: cross Abstract: Assistive devices for people with mobility impairments, such as powered exoskeletons, rely on accurate locomotion mode recognition to adapt control st
arXiv:2609.08253v1 Announce Type: new Abstract: Diffusion models have shown remarkable performance on diverse generation tasks. Recent work finds that imposing representation alignment on the hidden s
arXiv:2609.06635v1 Announce Type: cross Abstract: An image-augmentation pipeline must deliver a complete batch before a model can use it. We compare seven input paths from five libraries, starting wit