Knowledge catalogue
arXiv:2606.11260v1 Announce Type: cross Abstract: Humans process rich auditory environments through tightly integrated cognitive capabilities such as audio perception, audio reasoning, and memory. Des
arXiv:2606.11574v1 Announce Type: new Abstract: In many materials and product design problems, desirable candidates exhibit properties that fall within an acceptable range rather than achieve a single
arXiv:2606.11689v1 Announce Type: new Abstract: Composed Image Retrieval (CIR) constitutes a pivotal paradigm requiring models to perform joint reasoning on reference images and modification texts. Ho
arXiv:2606.12250v1 Announce Type: new Abstract: Large language models (LLMs) in medicine are mainly evaluated using multiple-choice question answering (MCQA), which can overestimate real clinical abil
arXiv:2603.00461v3 Announce Type: replace Abstract: We present ReMoT, a unified training paradigm to systematically address the fundamental shortcomings of VLMs in spatio-temporal consistency -- a cri
arXiv:2606.12412v1 Announce Type: cross Abstract: Vision-language models (VLMs) project images into hundreds to thousands of visual tokens, making decoder inference expensive in both attention computa
arXiv:2606.11192v1 Announce Type: new Abstract: We study restless bandits with binary latent states and imperfect binary feedback, motivated by opportunistic spectrum access with sensing errors. For t
arXiv:2601.17360v2 Announce Type: replace-cross Abstract: An adversary observing a model's released prediction can infer sensitive attributes of the queried input, or even reconstruct representatives
arXiv:2601.14792v2 Announce Type: replace Abstract: Despite their practical success, it remains unclear why Mixture of Experts (MoE) models can outperform dense networks beyond sheer parameter scaling
arXiv:2606.11275v1 Announce Type: cross Abstract: Rotary Position Embeddings (RoPE) make attention scores position-relative but leave the value pathway position-blind: the message sent by a value toke
arXiv:2512.14096v2 Announce Type: replace Abstract: Diffusion Transformers (DiTs) have achieved remarkable success in image generation, yet their deployment is hindered by high computational costs. We
This post discusses running Google's Gemma 4 QAT (Quantized Aware Training) 12B model on a GPU with 8GB of memory while maintaining a 16k token context window. The author likely shares performance ben
arXiv:2602.22962v2 Announce Type: replace Abstract: Data-driven models are revolutionizing weather forecasting. To optimize training efficiency and model performance, this paper analyzes empirical sca
arXiv:2606.11507v1 Announce Type: new Abstract: Mining hard, safety-critical scenes from driving logs is bottlenecked by the absence of difficulty labels, and no single proxy, collision risk, trajecto
arXiv:2606.11846v1 Announce Type: new Abstract: Current virtual staining approaches offer the potential for time- and cost-efficient biomarker quantification in cancer diagnostics and prognostics. How
arXiv:2606.12054v1 Announce Type: new Abstract: Injecting noise into the optimization process is a well-established technique for improving the training and generalization of deep neural networks. Yet
arXiv:2606.11518v1 Announce Type: cross Abstract: Fourier neural operators (FNOs) are effective and efficient surrogates for approximating solutions of PDEs and generalize across discretizations. Howe
arXiv:2606.12117v1 Announce Type: cross Abstract: Benchmark scores often misrepresent a large language model's (LLM's) knowledge, because they rely, e.g., on the model's ability to follow specific for
arXiv:2602.10908v2 Announce Type: replace Abstract: We present SoftMatcha 2, an ultra-fast and flexible search algorithm that enables search over trillion-scale natural language corpora in under 0.3 s
arXiv:2606.11657v1 Announce Type: cross Abstract: Generative AI emulators are increasingly used in scientific domains where we already have strong theory, benchmarks, and physical intuition. This rais
arXiv:2606.11814v1 Announce Type: cross Abstract: Machine-learning approaches to quantum state tomography can achieve high reconstruction fidelity, but the physical structure used by the trained model
arXiv:2606.11601v1 Announce Type: new Abstract: In fringe projection profilometry (FPP), depth is commonly recovered by fitting a phase-to-depth relation independently at each camera pixel. Although s
arXiv:2606.12382v1 Announce Type: cross Abstract: The Strength Pareto Evolutionary Algorithm 2 (SPEA2) is a popular and prominent evolutionary algorithm for solving multi-objective optimisation proble
arXiv:2606.11244v1 Announce Type: cross Abstract: Efficient large language model (LLM) serving is increasingly constrained by deployment cost. Quantization is a key technique for reducing serving cost
arXiv:2412.09023v3 Announce Type: replace Abstract: Channel and spatial attention mechanisms introduced in earlier work enhance the representational capabilities of deep convolutional neural networks
arXiv:2601.04710v2 Announce Type: replace Abstract: Fine-tuning large language models (LLMs) achieves strong performance but is often limited by the memory overhead of backpropagation. Zeroth-order (Z
arXiv:2606.11712v1 Announce Type: cross Abstract: User-side memory in LLMs is typically scored as a single 'personalization' capability: given a user's history, is the output more user-aware? We show
arXiv:2606.11348v1 Announce Type: new Abstract: Clock Tree Synthesis (CTS) is a computationally expensive stage in the physical design flow, requiring iterative EDA tool invocations to navigate a vast
arXiv:2606.12392v1 Announce Type: cross Abstract: Recently, large language models (LLMs) have achieved promising progress in the fields of classical Chinese translation and the generation of classical
arXiv:2606.12069v1 Announce Type: new Abstract: Touch is the primary medium through which humans interact with the environment. Currently, tactile learning mainly focuses on image-level pretraining or
arXiv:2606.12387v1 Announce Type: cross Abstract: Large Language Models (LLMs) have democratized database access through Text-to-SQL, but moving from prototypes to production remains difficult. Real d
arXiv:2606.11889v1 Announce Type: cross Abstract: Vision-language models (VLMs) are increasingly used for scene understanding in autonomous driving, but robustness analysis often relies on task-agnost
arXiv:2606.11552v1 Announce Type: new Abstract: Large language models (LLMs) achieve remarkable performance across a wide range of tasks, but their autoregressive decoding process incurs substantial i
arXiv:2601.12164v3 Announce Type: replace-cross Abstract: Large language models (LLMs) are increasingly deployed as analytical tools across multilingual contexts, yet their outputs may carry systemati
The model subsidies will eventually end and this workflow of “creating loops that will prompt your agents” will result in massive amounts of code that’s not well understood that you will have to pay l
arXiv:2512.11393v2 Announce Type: replace Abstract: Humans can intuitively parallelise complex activities, but can a model predict this from observing a single person? Given one egocentric video, we i
arXiv:2606.12289v1 Announce Type: cross Abstract: As Artificial Intelligence models grow in complexity, interpretability has become an indispensable tool for understanding, debugging, and controlling
arXiv:2606.11198v1 Announce Type: cross Abstract: Retrieval-augmented generation (RAG) systems inject external knowledge to improve LLM outputs, yet the format of injected content -- distinct from its
arXiv:2511.00044v3 Announce Type: replace Abstract: Physical neural networks (PNNs) are promising candidates for next-generation computing, but existing demonstrations remain several orders of magnitu
arXiv:2606.11990v1 Announce Type: cross Abstract: Remaining Useful Life (RUL) prediction is essential for industrial predictive maintenance, yet many learning-based approaches rely on extensive featur
arXiv:2606.11625v1 Announce Type: new Abstract: Time-series foundation models (TSFMs) are increasingly explored as predictive experts within emerging agentic time-series systems. However, TSFMs exhibi
arXiv:2606.11637v1 Announce Type: new Abstract: Touch is a key modality for embodied agents to understand the physical world. Although recent work has incorporated tactile signals into language system
arXiv:2606.11926v1 Announce Type: cross Abstract: Scientific progress depends on a repeated loop of exploration, experimentation, and abstraction. Researchers test candidate directions, interpret the
arXiv:2606.11804v1 Announce Type: new Abstract: Trustworthy AI requires reliable data-processing pipelines, not only robust downstream predictive models. As an upstream component, data summarization d
arXiv:2606.11836v1 Announce Type: cross Abstract: This paper presents a novel data-free and training-free compression approach for speech foundation models using channelwise clustering via k-means. Mo
arXiv:2606.11477v1 Announce Type: cross Abstract: Correcting handwritten exams by hand is time-consuming and error-prone, particularly for large cohorts, while fully digital exams tend to force a dida
Up until yesterday, our entire MTS team has operated under the philosophy of tokenmaxxing as much as possible on Claude Max plans. With Fable, this may no longer be possible: - One of our team members
arXiv:2606.12252v1 Announce Type: cross Abstract: Training deep neural networks for clinical time-series analysis is computationally demanding, yet many healthcare settings lack the resources required
arXiv:2606.12373v1 Announce Type: new Abstract: Reinforcement Learning (RL) with verifiable environments has emerged as a powerful approach for enhancing the reasoning capabilities of Large Language M
arXiv:2606.12028v1 Announce Type: new Abstract: Generalizable robot manipulation requires not only task-level reasoning over unseen scenes, but also reliable grounding of visual plans into embodiment-
arXiv:2601.03792v2 Announce Type: replace Abstract: Large Language Models (LLMs) have demonstrated remarkable proficiency in general medical domains. However, their performance significantly degrades
arXiv:2511.21594v3 Announce Type: replace Abstract: Large language models (LLMs) achieve state-of-the-art results across many natural language tasks, but their internal mechanisms remain difficult to
arXiv:2606.11546v1 Announce Type: new Abstract: Vision-language models like CLIP can provide rich semantic priors for open-vocabulary object detection. However, jointly integrating both textual and vi
arXiv:2606.11906v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models have shown strong performance in language-conditioned robotic manipulation, yet their robustness to linguistic varia
arXiv:2601.22025v2 Announce Type: replace-cross Abstract: Evaluating Large Language Model (LLM) applications differs from conventional software testing because outputs are probabilistic, semantically
arXiv:2606.11502v1 Announce Type: cross Abstract: Language models can state that 'the Earth orbits the Sun' and, when role-playing Aristotle, assert the opposite. Recent work argues that persona adopt
arXiv:2606.12385v1 Announce Type: new Abstract: Modern LLM training pipelines increasingly rely on other models to generate data, filter corpora, judge outputs, and guide development decisions. These
This post documents a Wordle puzzle solution (puzzle #1,817) completed in 3 attempts out of 6 allowed guesses, showing the progression of letter feedback (gray for incorrect letters, yellow for correc
arXiv:2606.12072v1 Announce Type: new Abstract: Pretrained video generators are promising visual world models that exhibit emergent task-solving abilities; however, their reliance on detailed textual
arXiv:2606.12403v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models inherit semantic grounding from large-scale pretraining and perform competently across in-distribution manipulation