Knowledge catalogue
arXiv:2608.26744v1 Announce Type: new Abstract: Zero-shot classification needs efficient label retrieval and fine-grained visual reasoning, yet discriminative and generative vision-language models fai
arXiv:2512.13965v1 Announce Type: cross Abstract: We present Generative Monte Carlo (GMC), a novel paradigm for particle transport simulation that integrates generative artificial intelligence directl
arXiv:2608.26960v1 Announce Type: new Abstract: Rehearsal-free class-incremental learning (CIL) with LoRA adapters remains challenging because the low-rank subspaces updated across tasks evolve withou
arXiv:2608.26752v1 Announce Type: new Abstract: Glass surface detection (GSD) is critical for scene understanding and reconstruction, and yet remains challenging due to the transparency and reflectivi
arXiv:2608.26983v1 Announce Type: new Abstract: Organizing long-term memory for multimodal agents remains challenging because existing methods either suffer from expensive question-agnostic offline su
arXiv:2604.02324v2 Announce Type: replace-cross Abstract: Language models (LMs) are increasingly extended with new learnable vocabulary tokens for domain-specific tasks, such as Semantic-ID tokens in
arXiv:2608.26648v1 Announce Type: new Abstract: Many synthetic-image detectors produce accurate predictions but offer limited insight into how those decisions are formed. This paper introduces Hierarc
arXiv:2608.26665v1 Announce Type: new Abstract: Maritime vessel detectors often face scenes where hulls are small, low-contrast, or blurred, while wakes are longer and easier to detect. This creates a
arXiv:2505.15740v2 Announce Type: replace-cross Abstract: Formal methods play a crucial role in ensuring the reliability of critical systems through rigorous mathematical verification. However, their
arXiv:2608.27153v1 Announce Type: new Abstract: Correlation Clustering (CC) is a natural formulation of clustering in combinatorial optimization, which uses a graph representation of the input and doe
arXiv:2608.26779v1 Announce Type: new Abstract: Preference learning optimizes models using response pairs, yet the informativeness of these pairs is fundamentally shaped by the instructions from which
arXiv:2608.26137v1 Announce Type: new Abstract: Second-language (L2) English learners can rarely rehearse speaking with a partner. Speaking is also the most anxiety-laden skill. These gaps drive a fas
arXiv:2608.27395v1 Announce Type: cross Abstract: Video carries the temporal structure of the physical world, yet learning representations from it has remained computationally expensive: prevailing se
arXiv:2608.26714v1 Announce Type: cross Abstract: Diffusion-based Video Virtual Try-On (VVT) achieves high visual fidelity through bidirectional spatio-temporal modeling, but complete-clip dependence
arXiv:2608.27184v1 Announce Type: cross Abstract: Electronic design automation (EDA) has advanced engineering productivity through successive generations of tooling that progressively automate synthes
arXiv:2608.26175v1 Announce Type: cross Abstract: Extractive prompt compression promises to cut LLM inference costs by removing low-information tokens, and learned compressors such as LLMLingua-2 repo
arXiv:2608.26389v1 Announce Type: new Abstract: SVD-based low-rank compression has become a fast-growing direction for reducing the memory and computational cost of large language models (LLMs). Howev
arXiv:2510.06270v2 Announce Type: replace-cross Abstract: Multi-objective discrete optimization problems, such as molecular design, pose significant challenges due to their vast and unstructured combi
arXiv:2608.27429v1 Announce Type: new Abstract: Chemical reactions are fundamentally transformations in electron space, yet most machine learning approaches model them either through extit{de novo} ge
arXiv:2608.26848v1 Announce Type: cross Abstract: Medical Visual Question Answering (Med-VQA) holds significant promise for clinical decision support, yet faces challenges due to limited annotated dat
arXiv:2608.26545v1 Announce Type: new Abstract: Robot policies deployed in the wild should have the capability to continually learn new tasks without forgetting existing behaviors. A common approach t
arXiv:2510.18383v4 Announce Type: replace-cross Abstract: Distilling the tool-use capabilities of large language models (LLMs) into small language models (SLMs) is essential for their practical applic
arXiv:2608.26149v1 Announce Type: new Abstract: Multi-table learning remains a major challenge in machine learning for healthcare and other complex information systems. Relational data combine several
arXiv:2608.26879v1 Announce Type: new Abstract: Fusing multiple modalities is expected to improve model performance. However, on the MultiHuSE dataset, early, late, and symmetric attention fusion ofte
arXiv:2608.26806v1 Announce Type: new Abstract: With the growing demand for processing multiple image sequences in real-world applications, various visual token pruning methods have emerged to mitigat
arXiv:2608.27039v1 Announce Type: cross Abstract: Accurately forecasting the movement of people in complex scenes requires reasoning over the past and present state of the entire environment. In this
arXiv:2608.26951v1 Announce Type: cross Abstract: Feed-forward 3D Gaussian Splatting reconstructs an explicit Gaussian representation from multiple input images in one network execution, making 3D rec
arXiv:2608.26530v1 Announce Type: new Abstract: Long-horizon agent runs generate experience that can improve both the current run and future work. Most self-improvement methods process this experience
arXiv:2504.12588v4 Announce Type: replace-cross Abstract: Transformers have attained outstanding performance across various modalities, owing to their simple but powerful scaled-dot-product (SDP) atte
arXiv:2608.26142v1 Announce Type: cross Abstract: Referring Expression Segmentation (RES) aims to generate pixel-wise segmentation masks from complex and implicit textual queries. While recent advance
arXiv:2608.27165v1 Announce Type: new Abstract: Autoregressive large language models (LLMs) routinely generate factually incorrect outputs with high decoding confidence, limiting their deployment in h
arXiv:2608.26238v1 Announce Type: new Abstract: Native 3D generators now recover impressive mesh geometry from a single image. However, a dense mesh stays soft where a machined object should be sharp,
arXiv:2608.26334v1 Announce Type: new Abstract: Automated theorem proving offers a natural foundation for recursive self-improvement in scientific discovery. However, existing neural provers do not fu
EDIT: Though the issue with q8 kv cache seems to arise from when and how often we run the quantize step, not that kv quantizing can't ever work - see comments for various proposed solutions --- One of
I've got Qwen3.8-Flash-next running on RTX 3090, Ryzen 9 3950X, a PCIe 3.0 motherboard, and 64GB DDR RAM from 2020. IQ4_XS weights, full kvarn5 context, vision on GPU, experts in host RAM, n-grams on
arXiv:2608.26684v1 Announce Type: new Abstract: Recent large language models achieve strong performance on complex reasoning tasks, where reinforcement learning with Group Relative Policy Optimization
arXiv:2608.27036v1 Announce Type: new Abstract: Large Language Models (LLMs) can be trained to perform chain-of-thoughts reasoning in order to improve the reliability of their responses. In this work,
arXiv:2608.27407v1 Announce Type: new Abstract: Estimation of Human-Object Interactions in 3D (3D HOI) is a fundamental problem in 3D computer vision with applications in AR/VR, robotics, and embodied
arXiv:2608.27439v1 Announce Type: cross Abstract: LLM-based agents are increasingly deployed in product-level execution harnesses, where jailbreaks can trigger harmful tool use and persistent state ch
arXiv:2608.26694v1 Announce Type: new Abstract: Detecting AI-generated text (AIGT) remains challenging because existing approaches rely on token-level statistical signals or independent stylometric fe
arXiv:2608.26732v1 Announce Type: cross Abstract: Graph neural networks (GNNs) are typically conceptualized as message-passing neural networks, yet it remains unclear why neighborhood aggregation reli
arXiv:2608.26956v1 Announce Type: new Abstract: Reward models play an essential role in aligning visual generative models, yet most existing visual reward models use a single scalar score or rely on f
arXiv:2608.26829v1 Announce Type: cross Abstract: Time series forecasting models operate on raw numerical sequences, lacking the semantic knowledge that domain experts implicitly leverage, such as the
arXiv:2608.26218v1 Announce Type: new Abstract: A coding agent combines a model with a harness, which decides what the model sees, which tools it can use, and how the work continues. We ask whether ch
arXiv:2607.19326v2 Announce Type: replace Abstract: Low-rank adaptation introduces a static learned update applied identically to every input. The update provides task-level adaptation but does not ex
arXiv:2608.26872v1 Announce Type: new Abstract: On-policy distillation (OPD), which leverages a pre-trained, specialized teacher model to provide dense supervisory signals, has achieved significant su
arXiv:2606.18801v2 Announce Type: replace-cross Abstract: With the rapid expansion of massive multilingual corpora, Multilingual Information Retrieval (MLIR) has emerged as a critical technology for g
arXiv:2505.20781v2 Announce Type: replace-cross Abstract: Off-policy evaluation (OPE) estimates the performance of a target policy using offline data collected from a behavior policy, and is crucial i
arXiv:2608.26437v1 Announce Type: new Abstract: Graph neural networks (GNNs) can exhibit unfair behavior even when sensitive attributes are excluded from node features, because graph topology and mess
arXiv:2601.08139v2 Announce Type: replace-cross Abstract: Vision-language models (VLMs), despite their extraordinary zero-shot capabilities, are vulnerable to distribution shifts. Test-time adaptation
arXiv:2608.26374v1 Announce Type: new Abstract: Diffusion language models (DLMs) generate text by iteratively denoising masked sequences, but standard decoding either fixes the sequence length or reli
arXiv:2608.26836v1 Announce Type: new Abstract: Large Language Models (LLMs) have demonstrated remarkable proficiency in natural language understanding, yet they struggle with strict multi-step reason
arXiv:2608.26923v1 Announce Type: new Abstract: We present TabuLM, the first language model pre-trained on Kinyarwanda tabular data. Kinyarwanda is a morphologically rich Bantu language spoken by over
arXiv:2608.27282v1 Announce Type: cross Abstract: Most single-stage 3D object detectors complete different tasks with the same extracted features. Nevertheless, it is impossible to project features in
arXiv:2608.26126v1 Announce Type: new Abstract: Telecommunications is a high-leverage domain for large language model (LLM)-based reasoning because routine engineering workflows require joint groundin
arXiv:2608.27175v1 Announce Type: new Abstract: Many Earth Observation applications need land-use/land-cover maps that are both precise and frequently updated, yet the strongest Earth Observation foun
arXiv:2608.26624v1 Announce Type: new Abstract: Open-vocabulary semantic segmentation (OVSS) aims to segment image regions corresponding to arbitrary text queries. Although the Segment Anything Model
arXiv:2606.22179v2 Announce Type: replace Abstract: Large language models (LLMs) are increasingly deployed as black-box classifiers in pipelines that automate confident decisions and route uncertain o
Hey all, and hello fellow DGX Spark-ers! Today I managed some pretty crazy numbers: 181 tok/s aggregate on 2× DGX Spark on Qwen3.8-Flash-Next at 512Kcontext (2.8M kvc) I hit 181 tok/s aggregate today
Hey everyone, I am the co-founder of Tontaube. My brother and I just released TontaubeV1, a 2.9B-parameter open-weight TTS model focused on expressive speech, long-form generation, and low-latency loc