Knowledge catalogue
arXiv:2609.30939v1 Announce Type: new Abstract: Cognitive behavioral therapy (CBT) is an evidence-based first-line treatment for depression, yet its scale is constrained by the time clinicians spend o
arXiv:2609.30288v1 Announce Type: new Abstract: In Transformer-based masked language models, attention is the primary mechanism for context mixing, but there are other ways to mix data across tokens.
arXiv:2609.30855v1 Announce Type: new Abstract: Reliable skin lesion segmentation and classification are central to dermoscopic computer-aided diagnosis. Existing multi-task frameworks couple the two
arXiv:2609.30746v1 Announce Type: new Abstract: Extreme events in chaotic systems are difficult to learn from short trajectories because they are controlled by transient finite-time instability rather
arXiv:2511.06157v3 Announce Type: replace-cross Abstract: Discovering high performing model architectures for wearables-based Human Activity Recognition (HAR) applications is challenging. The astonish
link to original article TLDR: security researcher eddie zhang used a modified+uncensored local qwen 3.8 27b to create an executable capable of dumping LSASS memory for credential harvesting while eva
arXiv:2609.30967v1 Announce Type: new Abstract: Most work on improving large language models treats accuracy as the sole objective. We argue that the harness, the Python code surrounding the model tha
arXiv:2609.31261v1 Announce Type: cross Abstract: The quadratic complexity of dense self-attention remains a central bottleneck for long-context language modeling. Many efficient alternatives address
arXiv:2609.31511v1 Announce Type: new Abstract: We present Muslim, a production Arabic voice AI platform serving grounded, sourced Islamic knowledge to real users. Beyond a real-time voice pipeline (N
arXiv:2609.30952v1 Announce Type: cross Abstract: Multi-view video understanding requires integrating spatial and temporal evidence across multiple, often non-overlapping camera streams: tracking enti
arXiv:2609.30718v1 Announce Type: new Abstract: High-fidelity simulation of control-conditioned multi-event physical systems is computationally expensive, especially across broad control spaces and lo
arXiv:2604.05904v2 Announce Type: replace-cross Abstract: Gray-box RC models are widely used to enable energy-efficient model predictive control (MPC) in buildings. However, estimating RC parameters r
arXiv:2609.31167v1 Announce Type: new Abstract: EEG foundation models increasingly use masked prediction to learn from unlabeled recordings, but optimizing this objective does not ensure transferable
arXiv:2609.31056v1 Announce Type: new Abstract: Machine unlearning aims to remove targeted information while preserving a model's other abilities. In realistic settings, such as privacy requests under
arXiv:2609.31600v1 Announce Type: new Abstract: Low-rank adapters (LoRA) make it cheap to fine-tune a large language model once per task, but combining several independently trained adapters into one
arXiv:2609.31539v1 Announce Type: new Abstract: Physics-Informed Neural Networks (PINNs) build neural representations of time-dependent PDE solutions, naturally incorporating physics knowledge and obs
Model Developer: NVIDIA Corporation Model Development: Fine-tuned from NVIDIA-Nemotron-3-Ultra-550B-A55B What is Nemotron? NVIDIA Nemotron™ is a family of open models with open weights, training data,
arXiv:2609.30688v1 Announce Type: cross Abstract: This study conducts a systematic hyperparameter search across five deep learning architectures, DLinear, LSTM, PatchTST, ResAttLstm, and Mamba2, and n
arXiv:2609.31559v1 Announce Type: new Abstract: Online learning in non-stationary environments requires models to adapt rapidly from streaming data under strict computational constraints. A principled
arXiv:2609.31356v1 Announce Type: new Abstract: Vision-Language Models (VLMs) exhibit remarkable zero-shot generalization, yet they often encode unwanted or hazardous stylistic domains such as idealiz
arXiv:2609.31364v1 Announce Type: new Abstract: Predicting human gaze is a core capability for applications ranging from web/UI design analysis to robotics and human-computer interaction. Yet, most vi
arXiv:2609.30749v1 Announce Type: new Abstract: Data Science Code Translation (DSCT) is the process of converting code between data science libraries while preserving functional equivalence and enabli
arXiv:2609.30316v1 Announce Type: cross Abstract: Language models used in financial backtests suffer from look-ahead bias, as a model trained on text published after the study period has already obser
arXiv:2609.30713v1 Announce Type: cross Abstract: Estimation of parameter of probabilistic models is an important task in the field of machine learning.For models of discrete variables, calculation of
Personal agents gone wrong. As we embrace more personal agents to carry out personalized tasks in the real world, interesting dynamics and behaviors will emerge. I think personal agents as they stand
arXiv:2608.25097v2 Announce Type: replace Abstract: Understanding how (multimodal) large language models perform on physics problems requires benchmarks that reflect the difficulty and breadth of expe
arXiv:2609.30684v1 Announce Type: new Abstract: Brazil's Pix settles about 5.9 billion instant, irreversible transfers a month. A fraudulent transfer can be recovered only while the funds remain in a
arXiv:2606.14929v2 Announce Type: replace-cross Abstract: Modern recommendation systems increasingly rely on dynamically routing diverse queries to multiple embedding models. Despite its practical sig
arXiv:2412.03072v2 Announce Type: replace Abstract: Strategy learning in game environments with multi-agent is a challenging problem. Since each agent's reward is determined by the joint strategy, a g
arXiv:2609.31468v1 Announce Type: cross Abstract: LLMs increasingly act as purchasing agents, which makes the LLM, not the user, the one choosing among the options that satisfy a request; its preferen
arXiv:2512.09172v3 Announce Type: replace-cross Abstract: We tackle continual adaptation of vision-language models to new attributes, objects, and their compositions in Compositional Zero-Shot Learnin
arXiv:2609.30836v1 Announce Type: new Abstract: Deploying small language models (SLMs) on offline, resource-constrained edge devices such as remote sensing satellites presents a fundamental challenge:
arXiv:2609.30592v1 Announce Type: cross Abstract: In standard attention, three separately learned projections decide how strongly a token attends to each neighbor (W_Q, W_K) and how the attended featu
arXiv:2609.31070v1 Announce Type: cross Abstract: Quantum Machine Learning is a novel field of research aimed at devising machine learning approaches exploiting principles of quantum mechanics, such a
arXiv:2609.30769v1 Announce Type: new Abstract: Cross-domain few-shot learning requires adapting a classifier to a new visual domain from very few labelled examples without target-time parameter updat
https://preview.redd.it/23cumykhabsh1.png?width=944&format=png&auto=webp&s=0b1d1c437fc845169f521b31793e2b1325dab0dd Reminder that you can put Qwen 3.8 27B as a subagent and its a workhorse. Pic: using
Six months ago, a result like this was unthinkable. But now we can say it loud and clear: local models are at the cutting edge, and the gap of just a few months has been confirmed. Personally, I use Q
I benchmarked Qwen3-VL 8B Instruct (Q4_K_M, Ollama, M5 24GB, ~30s/doc) against Claude Opus 5.5, Sonnet 5 and GPT-5.6 Terra on: - receipts: CORD (Indonesia) and SROIE (Malaysia), 30 each - 20 scanned 1
arXiv:2609.30465v1 Announce Type: cross Abstract: Mixture-of-experts (MoE) models activate few experts per token but store the full expert pool. Expert pruning reduces this storage burden; at a fixed
arXiv:2609.31028v1 Announce Type: new Abstract: Vision-language models (VLMs) achieve strong zero-shot (ZS) classification on histology images but do not perform as well on cytology, whose stains and
arXiv:2505.05848v3 Announce Type: replace Abstract: Modern 3D reconstruction and novel view synthesis approaches have demonstrated strong performance on scenes with opaque, non-refractive objects. How
arXiv:2609.30715v1 Announce Type: new Abstract: Learned robot policies produce actions, but their outputs alone do not establish whether execution is progressing as intended. Robot execution monitorin
arXiv:2609.30918v1 Announce Type: cross Abstract: Robust counterfactual explanations promise recourse that still works after the model behind it changes. Whether they keep that promise depends on what
arXiv:2609.31245v1 Announce Type: new Abstract: Individuals turn to large language models (LLMs) for guidance across a wide range of economic tasks, from comparing loan options and planning savings to
arXiv:2609.31082v1 Announce Type: new Abstract: Knowing where species occur is fundamental for biodiversity research and conservation. Species distribution models (SDMs) link species observations to e
arXiv:2609.31507v1 Announce Type: new Abstract: Urban uncrewed aerial vehicle (UAV) vision-language navigation (VLN) requires agents to follow instructions across extended urban spaces, inherently dem
arXiv:2609.31483v1 Announce Type: cross Abstract: Density functional theory (DFT) strikes a practical balance between accuracy and computational cost in many problems of computational chemistry and ma
arXiv:2609.30971v1 Announce Type: new Abstract: Embodied agents offer a promising route to automating scientific experimentation, yet their progress is constrained by the lack of reliable and systemat
arXiv:2606.13020v3 Announce Type: replace Abstract: Three paradigmatic forms of inference recur across scientific reasoning: deduction, induction, and causal abduction. Reliably evaluating LLMs on the
arXiv:2609.30325v1 Announce Type: new Abstract: Agents are increasingly deployed with real autonomy in web application and network penetration testing, where a single out-of-scope action can breach a
arXiv:2609.30814v1 Announce Type: new Abstract: Reliable absolute pose estimation in urban environments is undermined by outlier measurements and incorrect temporal associations that can persist in ti
TL;DR -- You should probably just use base Qwen3.6-35B, as only Occamy-1.0 is competitive with it. Tiel is a major let-down, worse than Ornith. KAT surprises (good), Nex surprises (bad). This post is
arXiv:2609.31148v1 Announce Type: new Abstract: Recent advances in sign language understanding have achieved impressive success on short, single-sentence videos, yet their performance drops sharply wh
arXiv:2609.30987v1 Announce Type: new Abstract: Self-supervised monocular depth estimation (MDE) enables depth prediction from monocular images without requiring ground-truth supervision, making it at
arXiv:2609.31206v1 Announce Type: new Abstract: Auroral spectrographs such as the Auroral Spectrograph In Skibotn (ASIS) record hundreds of thousands of emission spectra, but only a few hundred can be
arXiv:2609.31176v1 Announce Type: new Abstract: Repository-level issue localization aims to identify and rank the files and functions relevant to resolving a reported issue. LLM agents approach this t
arXiv:2609.30295v1 Announce Type: cross Abstract: Identifying an unfamiliar sign is difficult when a learner remembers its movement but does not know its meaning or formal feature codes. SignTrace add
arXiv:2504.06188v3 Announce Type: replace Abstract: AI agents can extend their capabilities at inference time by loading reusable skills into context, yet equipping an agent with too many skills, part
arXiv:2609.31291v1 Announce Type: cross Abstract: Large vocabularies make output heads a substantial inference cost in small language models. We propose softmax reparameterization, a post-training met
I know most people here probably don't care as much about sonnet 5.5 as they did opus 5.5, because their 100 and 200 plans already give them plenty of weekly usage for opus. But keep in mind: free use