Knowledge catalogue
arXiv:2609.06898v1 Announce Type: cross Abstract: Byte Pair Encoding (BPE) constructs vocabularies through greedy pair merging, but the resulting merge order does not necessarily allocate a fixed mode
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:2507.10383v5 Announce Type: replace-cross Abstract: Recurrent neural networks are canonical models of biological memory. In these models, memories are represented by distributed patterns of neur
arXiv:2609.05506v1 Announce Type: cross Abstract: We propose ECHO for dyadic 3D facial motion generation under a strict dual-stream audio-only setting, formulating the problem as an asymmetric task in
arXiv:2609.06663v1 Announce Type: cross Abstract: Although multimodal Large Language Models (MLLMs) excel in diverse tasks, their scalability remains limited by the memory and computational overhead o
arXiv:2609.08570v1 Announce Type: new Abstract: Microscopic image analysis has long been recognized as a promising approach for monitoring activated sludge. In recent years, deep learning-based image
arXiv:2609.07031v1 Announce Type: new Abstract: Learning with group invariances is central to many scientific and geometric learning problems, yet its computational foundations remain poorly understoo
arXiv:2609.07561v1 Announce Type: cross Abstract: Late-interaction models such as ColBERT achieve strong effectiveness by representing each document with many token-level vectors, but this expressivit
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:2508.20850v3 Announce Type: replace-cross Abstract: This study proposes a transferable encoding strategy that maps tactile sensor data to electrical stimulation patterns, enabling neural organoi
arXiv:2602.17196v2 Announce Type: replace Abstract: Multimodal large language models (MLLMs) incur substantial inference cost due to the processing of hundreds of visual tokens per image. Although tok
arXiv:2609.08381v1 Announce Type: new Abstract: Equivariant networks are commonly trained with Adam, yet recent work reports that matrix-structured optimizers such as Muon can perform better on these
arXiv:2602.02914v3 Announce Type: replace Abstract: Privacy-preserving face recognition (PPFR) hides facial appearance while retaining machine recognition, whereas perception-preserving face de-identi
arXiv:2609.06196v1 Announce Type: cross Abstract: We study the computational effort required for global optimization of a smooth, possibly nonconvex objective Gamma:R^doR. An algorithm satisfies the (
arXiv:2609.06862v1 Announce Type: new Abstract: Superposition refers to neural networks representing more features than they have dimensions. It offers a possible explanation for polysemantic neurons
arXiv:2609.07403v1 Announce Type: new Abstract: Privacy-sensitive surveillance systems could benefit from large vision-language models (VLMs), but such models typically require centralized access to r
arXiv:2609.08593v1 Announce Type: cross Abstract: Integrating generative adversarial networks (GANs) into federated semantic communication (SemCom) is a natural progression, as generative priors can r
arXiv:2603.18493v2 Announce Type: replace Abstract: Streaming 3D reconstruction maintains a persistent latent state that is updated online from incoming frames, enabling constant-memory inference. A k
arXiv:2609.07147v1 Announce Type: new Abstract: Federated learning, as a privacy-preserving distributed machine learning paradigm, faces significant threats from backdoor attacks. Compared to centrali
arXiv:2609.07010v1 Announce Type: new Abstract: Multimodal sentiment analysis often remains text-dominant due to raw-video noise and insufficient temporal modeling. Using CH-SIMS v2.0S, this study pro
arXiv:2609.05959v1 Announce Type: new Abstract: Human-Object Interaction (HOI) detection aims to localize humans and objects in images and classify their interactions. Zero-shot HOI focuses on recogni
arXiv:2609.08848v1 Announce Type: new Abstract: We present FIRE3D, a unified framework that takes a single RGB image or casual RGB video and transforms it into simulation-ready 3D scene assets for gam
arXiv:2609.08961v1 Announce Type: cross Abstract: For a finite set O of Boolean functions, we consider the class of propositional formulas built using the functions in O as connectives. We determine,
arXiv:2609.08032v1 Announce Type: new Abstract: We introduce FlexMoGen, a novel framework for flexible human motion synthesis conditioned on both natural language descriptions and motion style referen
arXiv:2609.08620v1 Announce Type: cross Abstract: We address the challenge of scalable uncertainty quantification in large-scale scientific applications, where complex state-of-the-art machine learnin
arXiv:2609.07617v1 Announce Type: new Abstract: With the rise of live sports betting in recent years, tennis forecasting has expanded from pre-match prediction to models that update win probabilities
arXiv:2507.23768v2 Announce Type: replace-cross Abstract: Existing methods for transfer learning struggle to deal with situations where the source datasets are limited and not guaranteed to be well-al
arXiv:2609.06826v1 Announce Type: cross Abstract: This paper examines the theory of Invariant Structural Learning (ISL), which proposes a non-optimization approach to concept formation. Learning is in
arXiv:2609.08886v1 Announce Type: new Abstract: Language-guided robots need persistent scene memories to follow instructions, revisit objects, and resolve references to objects encountered over time.
arXiv:2609.07048v1 Announce Type: new Abstract: Vision-language models (VLMs) have recently shown excellent progress in open-ended image-to-text generation. However, their multimodal nature makes them
arXiv:2609.07346v1 Announce Type: new Abstract: Radiance field representations such as 3D Gaussian Splatting (3DGS) enable high-quality novel view synthesis but can introduce complex, view-dependent a
arXiv:2601.18524v2 Announce Type: replace Abstract: Accurate prediction of nuclear magnetic resonance (NMR) chemical shifts is fundamental to spectral analysis and molecular structure elucidation, yet
arXiv:2609.08636v1 Announce Type: new Abstract: Egocentric 4D interaction forecasting aims to anticipate both where future interactions will occur in 3D and how the human body will move to realize the
arXiv:2609.06660v1 Announce Type: new Abstract: Accurate aerodynamic prediction is critical for designing fuel-efficient and safe transportation systems such as aircraft and automobiles, yet tradition
arXiv:2609.05662v1 Announce Type: new Abstract: Full-page end-to-end Optical Music Recognition seeks to transcribe entire music pages directly into symbolic notation, avoiding the limitations of tradi
arXiv:2609.06823v1 Announce Type: new Abstract: The next generation of artificial intelligence systems will likely be natively temporal and multimodal in both inputs and outputs: able to converse, per
arXiv:2609.06004v1 Announce Type: new Abstract: Quantitative spatial reasoning in visual-language models (VLMs) aims to infer spatial distances and directional relationships among objects in 3D space
arXiv:2601.09233v3 Announce Type: replace Abstract: The prevailing post-training paradigm for Large Reasoning Models (LRMs)---Supervised Fine-Tuning (SFT) followed by Reinforcement Learning (RL)-suffe
GPT‑6 Astra is OpenAI’s latest flagship model, outperforming GPT‑5.6 across virtually all common benchmarks—most noticeably in math, coding, and especially 3‑D rendering/animation tasks. The architect
arXiv:2609.07456v1 Announce Type: cross Abstract: We study the use of graph neural networks (GNNs) for finding approximate ground states of Ising models. Efficiently finding these ground states is of
arXiv:2609.08970v1 Announce Type: new Abstract: Industrial fraud detection often relies on costly expert-crafted features that overlook graph-structured relational signals, while GNNs often do not mee
arXiv:2609.05694v1 Announce Type: new Abstract: Predicting olfactory qualities from molecular structure is an open problem in chemoinformatics. Although linear models can link molecular features to od
Great study on what actually predicts vibe-coding ability. 100 tertiary-level students completed measures of computer-science achievement, domain-general cognitive skills and written-communication pro
arXiv:2609.08449v1 Announce Type: new Abstract: Gaussian splats provide a fast, high-fidelity representation for 3D objects but are often constructed from incomplete input data in practice, leaving mi
arXiv:2609.07749v1 Announce Type: new Abstract: Crowdsourcing platforms coordinate large pools of online workers who strategically choose which contests to enter and how much effort to invest. This se
arXiv:2609.06796v1 Announce Type: cross Abstract: Multi-chiplet photonic neural network accelerators (MCPNAs) combine photonic computation, photonic communica-tion, and heterogeneous chiplet integrati
arXiv:2609.07557v1 Announce Type: new Abstract: 3D Gaussian Splatting has recently revolutionised novel view synthesis as well as many other 3D vision methods and applications. Drawing inspiration fro
Sebastian Raschka’s September 2026 article introduces **GPT‑6 *Astra***, a next‑generation language model that expands upon the Transformer backbone with a novel *looped* architecture—allowing multipl
arXiv:2609.06307v1 Announce Type: cross Abstract: We study variational quantum distribution learning through a hierarchy of Walsh--Fourier approximations on the Boolean cube. At each level, a selected
arXiv:2311.01327v3 Announce Type: replace Abstract: We investigate the contextual bandits with knapsack (CBwK) problem in a high-dimensional linear setting, where the feature dimension can be very lar
Goodfire used Ai2’s fully open post-training stack to predict LLM behavioral changes, trace unwanted model behavior back to individual training examples, and test targeted fixes without sacrificing br
arXiv:2403.14293v3 Announce Type: replace Abstract: As robots become increasingly integrated into various industries, understanding how humans respond to robotic failures is critical. This study syste
arXiv:2603.26517v2 Announce Type: replace-cross Abstract: The discovery of constitutive laws from experimentally accessible measurements is a central problem in nonlinear computational mechanics. Many
arXiv:2609.08121v1 Announce Type: new Abstract: Low-rank tensor modeling has become an effective tool for hyperspectral anomaly detection. However, existing methods still suffer from high computationa
arXiv:2609.08286v1 Announce Type: new Abstract: Multi-scale modeling has become an effective approach for long-term time series forecasting, capturing temporal patterns that range from fine-grained lo
arXiv:2609.07596v1 Announce Type: cross Abstract: Vision-language models are increasingly used in settings where some input modalities may be unavailable, yet we know little about whether they can fai
I put together a mega write-up on GPT-6 Astra & looped transformers. How looped transformers / recurrent depth works, cost-tradeoffs, whether it hides reasoning traces, with lots of figures and a tour
arXiv:2505.21465v2 Announce Type: replace Abstract: Currently, a prevalent approach for enhancing Vision-Language Models (VLMs) performance is to encode both the high-resolution version and the thumbn
arXiv:2609.06279v1 Announce Type: cross Abstract: Learning-based manipulation requires supervision that is both semantically meaningful and physically executable, but current data pipelines often prov
arXiv:2609.07408v1 Announce Type: cross Abstract: This study investigates the classification of individuals as healthy or at risk of Parkinson's disease using machine learning (ML) models, focusing on