Knowledge catalogue
arXiv:2606.03097v1 Announce Type: new Abstract: Incorporating news into time series forecasting is appealing because news can reveal abrupt exogenous events that historical values alone cannot recover
arXiv:2606.02615v1 Announce Type: cross Abstract: Few-shot prompting provides an effective way to adapt auditory large language models to low-resource tasks such as children's speech recognition. Howe
arXiv:2606.02774v1 Announce Type: new Abstract: Vision-language models (VLMs) for autonomous driving have shown promising performance, but their ability to handle region-specific traffic rules remains
arXiv:2606.02967v1 Announce Type: cross Abstract: The space industry is quietly building toward something nobody has fully reckoned with: orbital data centers running thousands of autonomous AI worklo
arXiv:2606.02857v1 Announce Type: cross Abstract: Zeroth-order (ZO) optimization is a memory-efficient alternative to backpropagation for fine-tuning large language models, but its deployment is limit
arXiv:2606.03119v1 Announce Type: cross Abstract: Guidance methods, such as classifier-free guidance (CFG) and auto-guidance (AG), have advanced noise-to-data generation in diffusion models. Recently,
arXiv:2606.02628v1 Announce Type: cross Abstract: We investigate whether open-source LLMs encode a linearly separable truthfulness signal in their hidden states, and at which network depth this signal
Harvey just published a study showing a hybrid setup, open source GLM 5.1 as primary worker, routing to Opus 4.7 only when needed beats pure Opus 4.7 on quality and costs less. This is the multi-model
arXiv:2606.02767v1 Announce Type: cross Abstract: Kalman filtering performance is highly sensitive to model mismatch and noise covariance tuning. Learning-based approaches address these limitations bu
arXiv:2507.09105v4 Announce Type: replace Abstract: Earlier Sign Language Production (SLP) models typically relied on autoregressive decoding, which naturally preserves temporal causality but suffers
Ideogram released version 4.0 of its text-to-image model as an open-weight model with native 2K resolution, bounding box control, and improved text rendering. The model weights are available on GitHub
arXiv:2606.02994v1 Announce Type: new Abstract: ReAct-style LLM agents often rediscover the same reasoning routines across problems, yet leave those routines trapped in transient scratchpads. We intro
This post highlights four recent improvements to the ecosystem of open-weight large language models designed to run efficiently on consumer hardware, covering developments that make local LLM deployme
arXiv:2606.03437v1 Announce Type: new Abstract: Prior work has shown that instruction-tuned large language models (LLMs) are less well calibrated than their base pre-trained counterparts. However, lit
arXiv:2512.09106v4 Announce Type: replace Abstract: Diffusion (Large) Language Models (dLLMs) now match the downstream performance of their autoregressive counterparts on many tasks, while holding the
arXiv:2606.03246v1 Announce Type: new Abstract: The development on robust perception systems for Maritime Autonomous Surface Ships (MASS) is heavily constrained by the scarcity of diverse training dat
arXiv:2606.02996v1 Announce Type: cross Abstract: Inertial odometry (IO) using only Inertial Measurement Units (IMUs) provides a lightweight solution for human motion tracking in augmented reality (AR
arXiv:2606.03243v1 Announce Type: new Abstract: Modern text-to-image models have achieved strong visual synthesis, yet remain unreliable when prompts require implicit visual constraints, relational re
arXiv:2606.03291v1 Announce Type: new Abstract: Large language models (LLMs) can memorize sensitive facts, motivating unlearning methods that remove targeted knowledge without costly retraining. Howev
arXiv:2507.10419v3 Announce Type: replace-cross Abstract: We propose LoRA-MCL, a training scheme that extends next-token prediction in language models with a method designed to decode diverse, plausib
arXiv:2602.03681v2 Announce Type: replace Abstract: The quadratic computational complexity of softmax transformers has become a bottleneck in long-context scenarios. In contrast, linear attention mode
arXiv:2606.02946v1 Announce Type: new Abstract: Live streaming has emerged as a primary medium for social interaction and digital commerce, yet it is increasingly plagued by sophisticated risks. A fun
arXiv:2602.09708v2 Announce Type: replace-cross Abstract: We propose physics-informed spectral diffusion (PISD), a methodology that combines generative latent diffusion models with physics-informed ma
arXiv:2606.03989v1 Announce Type: new Abstract: Images composed of 2D pixel arrays are the standard input to computer vision algorithms, yet many underlying computations can be distributed across pixe
arXiv:2606.03428v1 Announce Type: cross Abstract: The large sizes of Spiking Vision Transformers (SViTs) still hinder their embedded implementation, highlighting the need for model compression. State-
arXiv:2508.03098v2 Announce Type: replace Abstract: Retrieval-Augmented Generation (RAG) enhances the factual accuracy of large language models (LLMs) by conditioning outputs on external knowledge sou
arXiv:2606.03257v1 Announce Type: cross Abstract: Spiking Vision Transformer (SViT) models are promising low-power ViT models for solving vision-based tasks with state-of-the-art performance. However,
arXiv:2606.03808v1 Announce Type: cross Abstract: We propose PURGE, a machine unlearning algorithm built on a simple but an under-exploited observation: continual learning (CL) and machine unlearning
arXiv:2606.03938v1 Announce Type: cross Abstract: Multi-epoch training is becoming the standard now that compute is growing faster than the supply of high-quality text. But pretraining a single model
arXiv:2606.03782v1 Announce Type: new Abstract: Large language models (LLMs) offer a promising approach to machine translation (MT) for extremely low-resource languages by incorporating linguistic res
arXiv:2606.03080v1 Announce Type: cross Abstract: Causal language models factorize sequence probabilities using only preceding context, leaving future information unexploited during training despite i
arXiv:2606.03019v1 Announce Type: cross Abstract: Copyleft, as implemented in licenses such as the GNU General Public License, was a legal hack that used copyright to guarantee user freedom by tying t
arXiv:2606.03234v1 Announce Type: new Abstract: Reinforcement Learning from Verifiable Rewards (RLVR) has become the dominant approach for improving mathematical reasoning in large language models, ye
arXiv:2606.03074v1 Announce Type: new Abstract: Diffusion models achieve high-fidelity radio map construction through iterative denoising, yet their sampling cost limits practicality in dynamic wirele
arXiv:2606.03219v1 Announce Type: new Abstract: African languages have very little labelled data, and it is unclear if augmenting the quantity of annotation data reliably enhances downstream performan
arXiv:2606.03517v1 Announce Type: cross Abstract: Training quantum neural networks (QNNs) on quantum hardware is currently bottlenecked by the cost of gradient estimation: standard parameter-shift met
arXiv:2606.02886v1 Announce Type: cross Abstract: Deep learning weather models now match numerical weather prediction accuracy while running orders of magnitude faster, but produce deterministic forec
arXiv:2606.02735v1 Announce Type: cross Abstract: Generalization remains a central bottleneck for vision-language-action (VLA) models: under distractors, appearance shifts, and semantically similar ta
arXiv:2606.03963v1 Announce Type: cross Abstract: Deep reinforcement learning has shown strong potential for enabling autonomous robots to learn complex navigational tasks. However, its practical use
arXiv:2606.03600v1 Announce Type: cross Abstract: Standard conformal prediction (CP) procedures are typically formulated in terms of p-values, but reliance on p-values alone limits flexibility, for ex
arXiv:2603.18599v2 Announce Type: replace Abstract: Speculative Jacobi Decoding (SJD) offers a draft-model-free approach to accelerate autoregressive text-to-image synthesis. However, the high-entropy
arXiv:2606.03610v1 Announce Type: new Abstract: Skeleton-based action recognition aims to understand human behaviors from body joint sequences and is especially challenging in the one-shot setting, wh
arXiv:2606.03056v1 Announce Type: new Abstract: As LLM agents adopt large skill libraries, selecting the right subset becomes a structural problem rather than a similarity-matching one: skills depend
arXiv:2606.03644v1 Announce Type: new Abstract: Comprehensive molecular profiling is essential for modern precision oncology but remains hindered by prohibitive costs, specimen exhaustion, and protrac
arXiv:2606.02842v1 Announce Type: new Abstract: Multimodal spatial reasoning often relies on long chains of intermediate textual and visual thoughts, where accumulating visual tokens and dense cross-m
Computex 2024 is expected to feature significant announcements around local AI deployment, with major industry players including NVIDIA and Microsoft actively promoting and discussing on-device AI wor
arXiv:2606.03508v1 Announce Type: new Abstract: Printed circuit board (PCB) defect detection is an essential part of automated optical inspection (AOI); yet it remains challenging in practice because
arXiv:2510.20372v4 Announce Type: replace-cross Abstract: Small influential data subsets can dramatically impact model conclusions, with a few data points overturning key findings. While recent work i
Thanks @hwchase17 @bryonkuchML for the inspiration and the nudge from @MEGAcodePaul - took your feedback seriously. I have developed a boilerplate that covers the full optimization loop that productio
arXiv:2501.02173v2 Announce Type: replace-cross Abstract: The deployment of Large Language Models (LLMs) in recommender systems for predicting Click-Through Rates (CTR) necessitates a delicate balance
arXiv:2606.03645v1 Announce Type: cross Abstract: Large Language Models exhibit paradoxical fragility in fundamental arithmetic, implying a disconnect between internal computation and discrete output.
arXiv:2606.02776v1 Announce Type: new Abstract: When large language models (LLMs) are used in high-stakes scenarios, such as legal, medical and financial advice, even a single conversation history is
arXiv:2606.02979v1 Announce Type: cross Abstract: We present a novel compact deep multi-task learning model to handle various autonomous driving perception tasks in one forward pass. The model perform
arXiv:2606.03655v1 Announce Type: new Abstract: Recent work in defeasible reasoning has seen notions of preferential semantics and entailment in the style of Kraus et al. applied to modal logics. Howe
arXiv:2606.03792v1 Announce Type: new Abstract: Low-Rank Adaptation (LoRA) successfully enables personalization in text-to-image generation by adapting pre-trained diffusion models to specific visual
arXiv:2606.02812v1 Announce Type: new Abstract: Modeling patient trajectories from longitudinal electronic health records (EHRs) requires reasoning over sparse, noisy, and long-context multimodal sequ
arXiv:2606.03112v1 Announce Type: cross Abstract: With the increasing scale and number of wind farms, wind turbines' daily operation and maintenance costs are increasing. To reduce operation and maint
arXiv:2603.04444v3 Announce Type: replace-cross Abstract: As large language models (LLMs) diversify across modalities, capabilities, and cost profiles, the problem of intelligent request routing -- se
arXiv:2602.14279v2 Announce Type: replace-cross Abstract: Eliciting information to reduce uncertainty about latent group-level properties from surveys and other collective assessments requires allocat
arXiv:2602.08873v2 Announce Type: replace-cross Abstract: Large language models (LLMs) are now used for academic expert recommendation. Existing audits typically evaluate such recommendations in isola