Knowledge catalogue
arXiv:2604.16917v1 Announce Type: new Abstract: Languages encode distinct abstractions and inductive priors, yet most large language models (LLMs) overlook this diversity by reasoning in a single domi
Attending #AIDev26 by @DeepLearningAI? Join @AI21Labs, @trychroma + @Baseten for a panel on optimizing modern AI systems. Drinks. Nikkei food. No fluff. April 28 | 5PM | Kaiyō SF Register → http://lum
arXiv:2603.11487v5 Announce Type: replace Abstract: Transformers often display an attention sink: probability mass concentrates on a fixed, content-agnostic position. Are sinks a byproduct of the opti
arXiv:2604.15594v1 Announce Type: cross Abstract: Modern datacenters schedule heterogeneous workloads across geo-distributed sites with diverse compute capacities, electricity prices, and thermal cond
arXiv:2510.20299v3 Announce Type: replace-cross Abstract: Brain tumors are a challenging problem in neuro-oncology, where early and precise diagnosis is important for successful treatment. Deep learni
arXiv:2403.18026v2 Announce Type: replace-cross Abstract: High-throughput biological imaging is often constrained by a trade-off between acquisition speed and image quality. Fast imaging modalities, s
arXiv:2604.15842v1 Announce Type: new Abstract: Large language models (LLMs) have demonstrated impressive capabilities, yet their internal mechanisms for handling reasoning-intensive tasks remain unde
arXiv:2604.16104v1 Announce Type: cross Abstract: Lung cancer remains one of the leading causes of cancer-related mortality worldwide. Conventional computed tomography (CT) imaging, while essential fo
arXiv:2604.15646v1 Announce Type: new Abstract: Clinicians exploring oncology trial repositories often need ad-hoc, multi-constraint queries over biomarkers, endpoints, interventions, and time, yet wr
arXiv:2604.15614v1 Announce Type: new Abstract: This paper proposes a novel method that incorporates empowerment when reasoning actions in reinforcement learning (RL), thereby achieving the flexibilit
arXiv:2604.15782v1 Announce Type: new Abstract: Traffic simulations, essential for planning urban transit infrastructure interventions, require vehicle-category-specific origin-destination (OD) data.
arXiv:2604.15772v1 Announce Type: new Abstract: Reinforcement learning (RL) often struggles in real-world tasks with high-dimensional state spaces and long horizons, where sparse or fixed rewards seve
arXiv:2604.15482v1 Announce Type: cross Abstract: Large Language Models (LLMs) unlearning is crucial for removing hazardous or privacy-leaking information from the model. Practical LLM unlearning dema
This newsletter covers three main topics: advances in automating alignment research to improve AI safety processes, a safety evaluation study of a Chinese AI model, and technical details about HiFloat
arXiv:2604.15729v1 Announce Type: cross Abstract: Whole Slide Image (WSI) analysis is pivotal in computational pathology, enabling cancer diagnosis by integrating morphological and architectural cues
arXiv:2604.15483v1 Announce Type: new Abstract: We present a new robotic foundation model, called {pi}_{0.7}, that can enable strong out-of-the-box performance in a wide range of scenarios. {pi}_{0.7}
arXiv:2510.22149v3 Announce Type: replace-cross Abstract: Federated learning (FL) has emerged as a promising paradigm for decentralized model training, enabling multiple clients to collaboratively lea
arXiv:2604.16106v1 Announce Type: cross Abstract: The Project of AI is a world-building endeavor, wherein those who fund and develop AI systems both operate through and seek to sustain networks of pow
arXiv:2604.15524v1 Announce Type: cross Abstract: This paper presents a novel density control framework for multi-robot systems with spatial safety and energy sustainability guarantees. Stochastic rob
arXiv:2604.15706v1 Announce Type: new Abstract: Everyday tasks come with a target, and pretraining models around this target is what turns them into experts. In this paper, we study target-oriented la
arXiv:2604.14882v1 Announce Type: cross Abstract: Rapid urbanization and continuous population growth have made municipal solid waste management increasingly challenging. These challenges highlight th
arXiv:2602.14517v2 Announce Type: replace Abstract: Large language models (LLMs) have achieved strong results in mathematical reasoning, and are increasingly deployed as tutoring and learning support
arXiv:2604.14630v1 Announce Type: new Abstract: Recent advances in unsupervised video object segmentation have highlighted the potential of two-stream architectures that integrate appearance and motio
arXiv:2510.08483v2 Announce Type: replace Abstract: Parallel scaling has emerged as a powerful paradigm to enhance reasoning capabilities in large language models (LLMs) by generating multiple Chain-o
arXiv:2411.00361v4 Announce Type: replace Abstract: Hierarchical reinforcement learning (HRL) enables agents to solve complex, long-horizon tasks by decomposing them into manageable sub-tasks. However
arXiv:2604.14322v1 Announce Type: cross Abstract: We derive a robust update rule for the online infinite hidden Markov model (iHMM) for when the streaming data contains outliers and the model is missp
arXiv:2604.14188v1 Announce Type: cross Abstract: Large language models have demonstrated impressive performance across many domains of mathematics and physics. One natural question is whether such mo
arXiv:2602.07529v3 Announce Type: replace Abstract: Large language models (LLMs) have demonstrated strong performance and rapid progress in a wide range of medical reasoning tasks. However, their sequ
arXiv:2604.14158v1 Announce Type: new Abstract: Current evaluations of long-term memory in LLMs are fundamentally static. By fixating on simple retrieval and short-context inference, they neglect the
arXiv:2604.15181v1 Announce Type: new Abstract: Extrapolative prediction of complex nonlinear dynamics remains a central challenge in engineering. This study proposes a one-shot learning method to ide
arXiv:2604.14888v1 Announce Type: new Abstract: Recent advances in vision language models (VLMs) offer reasoning capabilities, yet how these unfold and integrate visual and textual information remains
arXiv:2603.21094v3 Announce Type: replace Abstract: Human annotation is central to NLP evaluation, yet subjective tasks often exhibit substantial variability across annotators. While large language mo
arXiv:2509.12760v4 Announce Type: replace-cross Abstract: We introduce the Similarity-Distance-Magnitude (SDM) activation function, a more robust and interpretable formulation of the standard softmax
arXiv:2512.23578v3 Announce Type: replace Abstract: In this paper, we show that when spoken language models (SLMs) are instructed to speak in a specific speaking style at the beginning of a multi-turn
arXiv:2604.15010v1 Announce Type: cross Abstract: When do transformers commit to a decision, and what prevents them from correcting it? We introduce extbf{prolepsis}: a transformer commits early, task
arXiv:2211.16780v3 Announce Type: replace-cross Abstract: In online incremental learning, data continuously arrives with substantial distributional shifts, creating a significant challenge because pre
arXiv:2603.27064v2 Announce Type: replace-cross Abstract: Understanding charts requires models to jointly reason over geometric visual patterns, structured numerical data, and natural language -- a ca
arXiv:2604.13816v1 Announce Type: new Abstract: Determining the number of clusters is a central challenge in unsupervised learning, where ground-truth labels are unavailable. The Silhouette coefficien
arXiv:2604.13761v1 Announce Type: new Abstract: Sparse mixture-of-experts (MoE) layers have been shown to substantially increase model capacity without a proportional increase in computational cost an
arXiv:2604.13371v1 Announce Type: new Abstract: Large Language Models (LLMs) are increasingly described as possessing strong reasoning capabilities, supported by high performance on mathematical, logi
arXiv:2604.13942v1 Announce Type: new Abstract: Recent vision-language-action (VLA) systems have demonstrated strong capabilities in embodied manipulation. However, most existing VLA policies rely on
arXiv:2604.13609v1 Announce Type: new Abstract: Reinforcement learners can attain high reward through novel unintended strategies. We study a Bayesian mitigation for general environments: we expand th
arXiv:2604.13226v1 Announce Type: new Abstract: Large Language Models (LLMs) rely heavily on Key-Value (KV) caching to minimize inference latency. However, standard KV caches are context-dependent: re
arXiv:2604.13074v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) serve as daily assistants for millions. However, their ability to generate responses aligned with individual pr
arXiv:2604.13542v1 Announce Type: new Abstract: The growth of compute-intensive AI tasks highlights the need to mitigate the processing costs and improve performance and energy efficiency. This necess
arXiv:2604.13847v1 Announce Type: new Abstract: While sparse attention mitigates the computational bottleneck of long-context LLM training, its distributed training process exhibits extreme heterogene
1/5 When we saw our Reducer (=LLM judge component in Maestro, our agentic framework, that selects the best output from parallel agent runs) consistently picking gold patches, we were sure Claude Opus
arXiv:2604.12497v1 Announce Type: new Abstract: Large language models (LLMs) can generate survey responses at low cost, but their reliability varies substantially across questions and is unknown befor
arXiv:2604.06812v2 Announce Type: replace Abstract: Large Language Models (LLMs) have demonstrated impressive capabilities in long-form generation, yet their application is hindered by the hallucinati
arXiv:2604.12491v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly deployed for tabular question answering, yet calibration on structured data is largely unstudied. This pap
arXiv:2604.12833v1 Announce Type: new Abstract: Vision-Language Models (VLMs) have shown remarkable performance, yet their security remains insufficiently understood. Existing adversarial studies focu
arXiv:2601.10398v3 Announce Type: replace Abstract: In LLM-based text-to-SQL systems, unanswerable and underspecified user queries may generate not only incorrect text but also executable programs tha
arXiv:2604.12537v1 Announce Type: cross Abstract: Vision-Language Models (VLMs) have achieved remarkable progress in multimodal understanding, yet their positional encoding mechanisms remain suboptima
arXiv:2604.12100v1 Announce Type: new Abstract: Whole-slide image (WSI) classification in computational pathology is commonly formulated as slide-level Multiple Instance Learning (MIL) with a single g
arXiv:2604.12807v1 Announce Type: cross Abstract: Satellite image restoration aims to improve image quality by compensating for degradations (e.g., noise and blur) introduced by the imaging system and
arXiv:2604.12219v1 Announce Type: cross Abstract: Video Diffusion Transformers have revolutionized high-fidelity video generation but suffer from the massive computational burden of self-attention. Wh
arXiv:2601.07177v2 Announce Type: replace-cross Abstract: Federated learning (FL) addresses privacy and data-silo issues in the training of large language models (LLMs). Most prior work focuses on imp
arXiv:2604.12046v1 Announce Type: new Abstract: Large language models (LLMs) often hallucinate in long-form generation. Existing approaches mainly improve factuality through post-hoc revision or reinf
arXiv:2604.12159v1 Announce Type: new Abstract: The task of video geolocalization aims to determine the precise GPS coordinates of a video's origin and map its trajectory; with applications in forensi
arXiv:2603.23916v2 Announce Type: replace-cross Abstract: Multimodal deception detection aims to identify deceptive behavior by analyzing audiovisual cues for forensics and security. In these high-sta