Knowledge catalogue
arXiv:2603.24929v2 Announce Type: replace Abstract: Understanding and quantifying uncertainty in large language model (LLM) outputs is critical for reliable deployment. However, traditional evaluation
arXiv:2608.02870v1 Announce Type: new Abstract: We introduce ours{}, a recurrent Transformer architecture with fixed-size memory that generalizes sliding-window attention while remaining parallelizabl
arXiv:2405.16440v2 Announce Type: replace-cross Abstract: In recent years, Transformers have become the de-facto architecture for long-term time series forecasting (LTSF), yet they face challenges ass
arXiv:2509.21012v4 Announce Type: replace-cross Abstract: In-context Learning (ICL) is an emerging few-shot learning paradigm based on modern Language Models (LMs), yet its inner mechanism remains unc
arXiv:2511.03942v2 Announce Type: replace-cross Abstract: We present MIDI-LLM, a recipe that improves multitrack text-to-MIDI generation via adapting Large Language Models (LLMs). MIDI-LLM expands an
TensorSharp's MoE CPU-offload feature has been merged into main. Here is the parameters description of this feature: Mixture-of-Experts CPU offload: --n-cpu-moe <N> | -ncmoe <N> Keep the routed MoE ex
arXiv:2608.03895v1 Announce Type: new Abstract: Camera-based bird's-eye-view (BEV) 3D detection typically assumes accurate and fixed camera extrinsics. In detectors using spatial cross-attention (SCA)
arXiv:2608.02999v1 Announce Type: new Abstract: Statistical regularities are routinely offered as evidence that undeciphered sign systems encode language; the Indus script debate is the canonical exam
arXiv:2608.02942v1 Announce Type: new Abstract: Diffusion language models (dLLMs) can predict many tokens in parallel, but accurate generation still requires many iterative denoising steps. Few-step d
arXiv:2608.03034v1 Announce Type: cross Abstract: Reasoning-enhanced large language models have achieved remarkable improvements in planning tasks, yet their deployment in embodied systems remains imp
arXiv:2608.03048v1 Announce Type: cross Abstract: Long-context reasoning remains a critical bottleneck for large language models, as recent recurrent-memory approaches face two inherent challenges: se
arXiv:2608.03579v1 Announce Type: cross Abstract: Modern multi-tenant Low-Rank Adapters (LoRAs) serving systems concurrently host tens to hundreds of LoRA adapters. Though powerful, this introduces a
arXiv:2608.03155v1 Announce Type: new Abstract: Autonomous exploration missions require decision-making under sensor uncertainty and computational constraints, yet integrating scientific representatio
arXiv:2608.03612v1 Announce Type: cross Abstract: Virtual contrast enhancement (VCE) synthesizes enhanced breast MR images from pre-contrast acquisitions. Modern latent generators offer strong image p
arXiv:2608.02713v1 Announce Type: cross Abstract: Continually improving agents require dynamic interaction feedback beyond static supervision, yet direct real-environment interaction is costly, slow,
Questions & Responses(in BOLD) below. Favorite question(s) moved to end of the thread with combined responses(removed duplicates). Be optimistic folks. I'm sure we're getting other models too apart fr
arXiv:2608.03219v1 Announce Type: new Abstract: Benchmark gains are often treated as evidence of greater LLM capability. Yet the same gain can reflect different changes in model behavior. A model may
arXiv:2512.03621v3 Announce Type: replace Abstract: Synthesizing multi-pass videos is important for autonomous driving. While current repair-based methods often struggle with out-of-distribution artif
arXiv:2608.03341v1 Announce Type: cross Abstract: Large language models (LLMs) have substantially improved code generation, yet achieving strong functional correctness remains difficult, especially fo
arXiv:2608.03228v1 Announce Type: new Abstract: Existing low rank KV cache methods preserve either model weights or key variance, neither of which directly reflects the attention scores used during in
Hey everyone! Scenema Audio is now a native ComfyUI custom node. Same model that powers scenema.ai now quantized so it fits on 8GB VRAM. When we first released it a few months ago as an API and Docker
arXiv:2608.03631v1 Announce Type: new Abstract: Spatial relation questions require a model to identify the queried subject and object before comparing their layout. Yet a VLM can recognize both entiti
arXiv:2607.28048v2 Announce Type: replace Abstract: Skill-based prompting has become a practical mechanism for improving large language model (LLM) agents, yet existing skill acquisition methods often
arXiv:2608.02625v1 Announce Type: cross Abstract: Diffusion language models (DLMs) can revise tokens bidirectionally, but standard decoding procedures often adapt them to left-to-right generation by p
arXiv:2603.14068v2 Announce Type: replace Abstract: In teleoperation of contact-rich manipulation tasks, selecting robot impedance is critical but difficult. The robot must be compliant to avoid damag
arXiv:2608.03231v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) policies promise general robotic manipulation, but their robustness against physical-world attacks remains fragile. In pa
arXiv:2608.03319v1 Announce Type: cross Abstract: Future integrated sensing and communication (ISAC) architectures separate the sensing entity (SE) that acquires measurements from the sensing function
arXiv:2608.03763v1 Announce Type: new Abstract: Zero-shot 3D visual grounding aims to localize specific objects based on textual descriptions and 3D visual input. However, the effectiveness of existin
arXiv:2608.02883v1 Announce Type: new Abstract: 3D point cloud registration in laparoscopic surgery estimates the transformation between an intraoperative organ reconstructed from video and its preope
arXiv:2608.03284v1 Announce Type: cross Abstract: Ensuring safety and policy compliance in text-to-image diffusion models remains a critical challenge, as benign or adversarial prompts can often elici
arXiv:2603.20381v2 Announce Type: replace-cross Abstract: Understanding the fundamental mechanisms governing the production of meaning in the processing of natural language is critical for designing s
arXiv:2608.02816v1 Announce Type: new Abstract: We study the topology of learned representations in predictive coding networks (PCNs), a neuro-inspired bidirectional architecture, using a quantitative
arXiv:2608.03727v1 Announce Type: new Abstract: Action labels tell a vision-language-action (VLA) policy which robot commands to imitate, but not how those commands change the 3D world. The aligned de
arXiv:2608.03150v1 Announce Type: new Abstract: Generative retrieval (GR) is a promising paradigm for industrial search advertising, yet its deployment is constrained by strict relevance and latency r
arXiv:2608.03467v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR) com- monly optimizes each correct completion as an independent learning signal. In GRPO, this comp
arXiv:2608.03342v1 Announce Type: cross Abstract: Conditional segmentation models may be trained and evaluated with auxiliary signals cleaner than those available at deployment. We study this protocol
arXiv:2608.01463v2 Announce Type: replace Abstract: Multi-agent debate commonly exchanges complete rationales even when disagreements concern only a few intermediate claims. We introduce Localized Mul
Xiaomi-Robotics-1 is a robot foundation model trained on over 100K hours of real-world manipulation trajectories. It is a Vision-Language-Action (VLA) model engineered for out-of-the-box mobile manipu
arXiv:2608.01185v1 Announce Type: new Abstract: Recent 3D vision-language models (3D VLMs) construct geometry aware tokens by projecting 2D visual features into world coordinates, enabling spatial rea
arXiv:2608.00180v1 Announce Type: new Abstract: Conflicting objectives are general in RL alignment, and training on them data-efficiently is hard. Training a safety guard with RL means optimizing two
arXiv:2608.01636v1 Announce Type: new Abstract: This paper studies feedback Nash equilibrium (FBNE) seeking for multi-agent trajectory planning in nonlinear dynamical systems with unknown agents' obje
arXiv:2608.02505v1 Announce Type: cross Abstract: Can scientific abduction occur without continuous sensorimotor embodiment? Recent arguments in AI and philosophy of science hold that genuine hypothes
arXiv:2608.02049v1 Announce Type: cross Abstract: Bosonic quantum systems provide a hardware-efficient platform for quantum information processing but remain challenging to characterise due to their l
arXiv:2608.01980v1 Announce Type: new Abstract: Chain-of-thought (CoT) reasoning can improve performance on difficult video questions but often wastes decoding tokens on simple ones. We study whether
Members of the Open Secure AI Alliance — now more than 120 organizations strong — are developing new guidelines to strengthen agentic AI cybersecurity as the annual Black Hat conference begins in Las
arXiv:2608.00796v1 Announce Type: cross Abstract: Automatic RF modulation recognition is of critical importance in spectrum monitoring, electronic warfare, and cognitive radio applications, where low
arXiv:2608.01691v1 Announce Type: cross Abstract: Detecting a change in a multivariate series answers only the first of two questions; the operational question is which coordinates changed. Existing a
arXiv:2608.00693v1 Announce Type: new Abstract: Schema linking is a critical component of Text-to-SQL systems, but existing approaches often trade off contextual modeling capacity, score-based control
arXiv:2608.02602v1 Announce Type: new Abstract: Language remains an outlier in generative modeling: while images, video, and audio are increasingly modeled in continuous latent spaces, text generation
sampler : remove 'full-context windows' from history-based samplers (#26524) Resolve -1 to 1024 instead of ctx-len for samplers Because of backend-sampling we initialize samplers before the complete l
arXiv:2608.00985v1 Announce Type: new Abstract: The rapid growth of single-cell transcriptomic data has enabled the development of foundation models pretrained primarily by reconstructing masked expre
arXiv:2511.20851v3 Announce Type: replace-cross Abstract: Feature selection remains difficult in modern high-dimensional settings, and established methods such as Boruta and Recursive Feature Eliminat
arXiv:2608.00442v1 Announce Type: new Abstract: Medical anomaly detection identifies abnormal images and localizes lesions under scarce supervision while generalizing across organs and modalities. Exi
arXiv:2608.01490v1 Announce Type: new Abstract: Binarizing a polynomial Kolmogorov--Arnold Network (KAN) not only changes parameter precision, but also alters the function space available to each laye
arXiv:2608.00678v1 Announce Type: new Abstract: Despite recent advances in Monocular Depth Estimation, state-of-the-art depth foundation models remain vulnerable to robustness issues. Particularly, ev
arXiv:2608.02305v1 Announce Type: new Abstract: Active feature acquisition (AFA) asks which unobserved feature to measure next for each test instance under a budget. Greedy rules are easy to train but
arXiv:2608.01753v1 Announce Type: new Abstract: Addressing urban blight has seen increased focus in the past 15 years. Assessing urban blight is essential for guiding urban planning, targeting rehabil
arXiv:2608.02326v1 Announce Type: new Abstract: Humans perform long-horizon manipulation by retaining knowledge of what earlier actions have established while continuously adapting the motion underway
Compute scarcity is not the only struggle AI teams face. Optimal utilization is also key. Friction also emerges when they outgrow informal coordination methods such as shared spreadsheets, manual SSH
arXiv:2608.01208v1 Announce Type: cross Abstract: For a trading desk, residual climate hedging valuation adjustment (HVA) is the climate cost left after its inherited hedge and any admissible overlay