Knowledge catalogue
mentria.ai is a browser inference engine I've been building solo, from scratch in WebGPU/WGSL. This week it crossed a milestone I had been chasing for a while: a 27B one-bit model answering at up to 3
arXiv:2609.05985v1 Announce Type: new Abstract: Robots that follow open-ended language instructions need to connect semantic intent to visual scene understanding, geometric feasibility, object states,
arXiv:2609.05919v1 Announce Type: new Abstract: We propose a graph dictionary learning (GDL) framework where each graph is represented as a zero-mean Gaussian distribution derived from its filtered La
arXiv:2609.08070v1 Announce Type: cross Abstract: The brain uses discrete spikes for dynamic computation, yet, how neural microcircuits (NMCs) solve temporal credit assignment using local spike timing
arXiv:2609.08307v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used as backends for intelligent web services, but serving them across the edge continuum requires balan
arXiv:2609.05503v1 Announce Type: new Abstract: Diffusion models have become the dominant family of generative models in the visual domain. However, their widespread public availability enables misuse
arXiv:2609.07821v1 Announce Type: cross Abstract: Chain-of-Thought (CoT) improves the reasoning ability of Large Language Models (LLMs) but incurs substantial computation and context costs. Existing m
arXiv:2609.07664v1 Announce Type: new Abstract: Deployment of Large Language Models (LLMs) on memory-constrained edge devices relies heavily on aggressive post-training quantization. However, evaluati
arXiv:2609.06723v1 Announce Type: new Abstract: Meshes remain the most practical representation for geometry reasoning and integration into graphics pipelines, yet existing reconstruction methods stru
arXiv:2609.06758v1 Announce Type: new Abstract: Visual generation is evolving from generative models used through a single invocation into agentic control processes that can plan, select tools, inspec
arXiv:2609.07961v1 Announce Type: cross Abstract: Graph modeling, a crucial task for representing complex relationships in graph-structured data, has achieved significant success in recent years. Howe
arXiv:2609.07154v1 Announce Type: new Abstract: We describe our entry to the EgoLongQA track of the Wearable-AI Challenge in ECCV 2026, which placed first in the <=2B parameter division with 0.8279 on
arXiv:2609.09030v1 Announce Type: cross Abstract: Chain-of-thought reasoning provides a structured computation between a model's input and final answer. Yet it is often evaluated through endpoint accu
arXiv:2609.08806v1 Announce Type: new Abstract: Arm pose estimation enables applications in fitness, extended reality input, rehabilitation, and life logging. Prior smartwatch-based approaches rely on
arXiv:2609.06656v1 Announce Type: new Abstract: Modern power systems are growing increasingly complex as they integrate diverse generation sources to meet rising demand, making accurate load forecasti
arXiv:2609.07917v1 Announce Type: new Abstract: Counterfactual explanations formalize 'what-if' scenarios by identifying modifications to an input instance that obtain a desired alternative prediction
arXiv:2609.06726v1 Announce Type: new Abstract: We present B2TFPose, a training-free zero-shot method for 6DoF pose estimation of unseen objects from RGB images. Using a single frozen DINOv3 vision tr
arXiv:2609.06076v1 Announce Type: new Abstract: Retraining-free MoE compression reduces deployment memory by pruning or merging experts, but often treats the compressed checkpoint as the final artifac
arXiv:2609.06394v1 Announce Type: cross Abstract: Massive datasets in modern machine learning have made data reduction a central challenge, particularly for clustering tasks where memory and computati
arXiv:2609.08673v1 Announce Type: new Abstract: Advances in tactile sensing have made contact-rich perception possible, accelerating progress in robotic manipulation, material understanding, and embod
arXiv:2609.08220v1 Announce Type: new Abstract: Large language models (LLMs) have recently emerged as a promising tool for automating robot design from high-level specifications, yet they remain ineff
arXiv:2609.05862v1 Announce Type: new Abstract: Learning on dynamic graphs is difficult when changes in the underlying network are only partially observed. Acquiring current graph information incurs o
arXiv:2609.06504v1 Announce Type: new Abstract: Memory facilitates question answering over long videos by extracting and retrieving facts to fit within the limited context windows of multimodal LLMs (
arXiv:2609.08419v1 Announce Type: new Abstract: Multiple Instance Learning (MIL) is widely used for weakly supervised learning, particularly in digital pathology, where fine-grained annotations are co
arXiv:2603.00039v2 Announce Type: replace Abstract: LLM-as-a-judge ensembles are the standard paradigm for scalable evaluation, but their aggregation mechanisms suffer from a fundamental flaw: they im
arXiv:2609.07094v1 Announce Type: new Abstract: Reasoning is a promising route to the generalization that autonomous driving requires in the long tail, as it can infer how the elements of a scene depe
arXiv:2609.08638v1 Announce Type: new Abstract: An action chunk can span several stages of a manipulation task, yet a label for its first step describes only the current stage. We introduce Chunk-Alig
arXiv:2609.08686v1 Announce Type: new Abstract: Long-form instructional videos require automatic chaptering to support browsing, navigation, and knowledge access. Recent long-context language models c
arXiv:2609.08709v1 Announce Type: new Abstract: Designing foundation models for graphs is challenging due to the irregular structure of graphs and the different sizes and characteristics of embeddings
arXiv:2609.07183v1 Announce Type: cross Abstract: Reinforcement learning with verifiable rewards (RLVR) is sensitive to which problems a model trains on, yet existing selection criteria--difficulty fi
arXiv:2510.09712v4 Announce Type: replace Abstract: The proliferation of Large Language Models (LLMs) has enabled a new class of psychologically grounded malicious comments, shifting fake news attacks
arXiv:2609.07838v1 Announce Type: new Abstract: Connected robotics is an emerging 6G application where mobile robots follow natural-language instructions to manipulate physical objects. The Vision-Lan
arXiv:2609.08999v1 Announce Type: new Abstract: Partially Relevant Video Retrieval (PRVR) retrieves untrimmed videos when queries describe only short moments. Although recent methods improve local rep
arXiv:2609.05454v1 Announce Type: cross Abstract: Oligonucleotide melting temperature is a fundamental determinant of nucleic acid hybridization and underpins the design of molecular diagnostics, poly
arXiv:2609.07314v1 Announce Type: cross Abstract: Rotary position embedding (RoPE) uses each token's integer position to determine the rotation applied inside attention. This works well for local toke
arXiv:2609.07070v1 Announce Type: new Abstract: Spatio-temporal context has become increasingly crucial for visual tracking. However, most existing approaches extract spatio-temporal cues via discrete
arXiv:2609.07529v1 Announce Type: new Abstract: Tool-augmented language agents are vulnerable to indirect prompt injection (IPI). Unlike direct prompt injection, IPI hides adversarial instructions in
arXiv:2609.07498v1 Announce Type: cross Abstract: Transferring human hand demonstrations to robotic grippers has recently emerged as a cost-effective solution for robot learning. However, existing met
arXiv:2609.06704v1 Announce Type: new Abstract: Chain-of-thought (CoT) may often look plausible, yet it may not faithfully reflect the model's decision-making process. While methods for measuring the
arXiv:2609.07499v1 Announce Type: new Abstract: Training-free collaborative pipelines that integrate Vision Foundation Models such as CLIP, SAM, and DINO achieve strong open-vocabulary dense predictio
arXiv:2609.06670v1 Announce Type: new Abstract: The In-context learning (ICL) paradigm aids large language models (LLMs) to adapt to new tasks without need for fine-tuning. However, selecting an optim
arXiv:2609.07072v1 Announce Type: new Abstract: Graphic designs, such as posters, advertisements, and infographics, are an important medium for communicating information and shaping understanding. Unl
arXiv:2601.01368v2 Announce Type: replace Abstract: Score-based causal discovery in the presence of unobserved confounders requires both a consistent scoring criterion and an efficient search over gra
arXiv:2609.08650v1 Announce Type: new Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) has been central to the recent success of Large Reasoning Models. However, while RLVR significantl
arXiv:2609.06809v1 Announce Type: new Abstract: Modern stereo matching models fail when disparity crosses zero, with end-point error (EPE) rising by 4.6-37imes. Yet stereoscopic content, from cinema 3
arXiv:2609.08337v1 Announce Type: new Abstract: On-policy distillation (OPD) transfers teacher knowledge on student-generated trajectories, but efficient sampled objectives reduce the teacher distribu
arXiv:2512.13742v3 Announce Type: replace Abstract: Medical image classifiers detect gastrointestinal diseases well, but they do not explain their decisions. Large language models can generate clinica
arXiv:2609.05842v1 Announce Type: cross Abstract: Reinforcement learning with verifiable rewards enables large language models to think slowly, but the same training can induce policy collapse: probab
arXiv:2609.06962v1 Announce Type: new Abstract: Real-world remote sensing image dehazing (RSID) remains challenging because atmospheric scattering, spatially non-uniform haze and colour distortion joi
arXiv:2609.08217v1 Announce Type: new Abstract: VLMs have shown promise for autonomous driving, yet still suffer from hallucination, weak spatio-temporal perception, and limited generalization. Recent
arXiv:2609.06055v1 Announce Type: new Abstract: Most end-to-end autonomous-driving systems learn by imitating human driving logs, leaving their learned behavior constrained by the quality and behavior
arXiv:2512.03936v2 Announce Type: replace Abstract: Autonomous driving planning systems perform nearly perfectly in routine scenarios using lightweight, rule-based methods but still struggle in dense
arXiv:2609.08850v1 Announce Type: new Abstract: Text-guided Video Temporal Grounding (VTG) aims to localize the relevant segments in an untrimmed video based on text queries, yet collecting dense temp
arXiv:2411.15876v3 Announce Type: replace-cross Abstract: Overfitting remains a significant challenge in deep learning, often arising from data outliers, noise, and limited training data. To address t
arXiv:2609.08164v1 Announce Type: new Abstract: Aerial Object Goal Navigation (ObjectNav) requires an unmanned aerial vehicle (UAV) to locate a described target in an unknown outdoor environment using
arXiv:2609.06520v1 Announce Type: cross Abstract: This work presents a control framework that enables a multicopter equipped with a two-axis gimbal to emulate the flight dynamics of a fixed-wing aircr
arXiv:2601.02856v4 Announce Type: replace Abstract: Precise day-ahead forecasts for electricity prices are crucial to ensure efficient portfolio management, support strategic decision-making for power
arXiv:2609.08025v1 Announce Type: cross Abstract: Reasoning agents increasingly rely on external tools such as web search to answer complex queries. Reinforcement learning (RL) finetuning algorithms s
arXiv:2609.08330v1 Announce Type: new Abstract: Table detection is a core task in document analysis, supporting downstream applications such as information retrieval, document reconstruction, and visu
arXiv:2609.05650v1 Announce Type: new Abstract: We propose a reinforcement learning framework in which exploration is driven by intrinsic curiosity, designed for scenarios where environments are non-s