Knowledge catalogue
arXiv:2605.18881v1 Announce Type: new Abstract: In dynamic flow fields, various animals exhibit remarkable odor search capabilities despite relying on stochastic detections. Interestingly, there exist
arXiv:2605.18820v1 Announce Type: cross Abstract: Superposition allows Transformers to reason in depth, carrying an entire reasoning frontier in parallel through a bounded-depth forward pass instead o
arXiv:2605.19630v1 Announce Type: new Abstract: With every advancement in generative AI models, forensics is under increasing pressure. The constant emergence of new generation techniques makes it imp
arXiv:2602.04381v2 Announce Type: replace-cross Abstract: Real-time polyp segmentation is essential for early colorectal cancer detection, yet clinical deployment remains blocked by GPU dependency. We
The security landscape is entering uncharted territory as quantum computing moves from theoretical threat to near-term enterprise reality — and the race to post-quantum encryption is one most organiza
arXiv:2605.19743v1 Announce Type: new Abstract: Large Language Model (LLM) agents are increasingly applied to engineering design tasks, yet existing evaluation frameworks do not adequately address mul
arXiv:2604.02784v2 Announce Type: replace-cross Abstract: Vision-Language Models (VLMs) excel at multimodal tasks, but they remain vulnerable to hallucinations that are factually incorrect or unground
arXiv:2410.18856v4 Announce Type: replace Abstract: Frontier large language models (LLMs), such as GPT-5, Claude 4.5, Gemini 3, Llama 4, and DeepSeek-R1, represent a transformative class of AI tools c
arXiv:2605.19556v1 Announce Type: new Abstract: Estimating relative pose from image pairs fundamentally requires only a minimal subset of geometrically consistent correspondences. However, most learni
arXiv:2605.18918v1 Announce Type: cross Abstract: Modern AI assistants are agentic. To answer a single user request, the underlying language model pulls in information from many sources, such as web s
arXiv:2605.19243v1 Announce Type: cross Abstract: We study the problem of recovering a globally consistent Euclidean embedding of data, given only a local distance graph and propose a method that opti
arXiv:2605.18872v1 Announce Type: cross Abstract: Robotic assembly in architectural construction faces a persistent bottleneck: existing planners are either highly specialized, requiring prohibitive r
arXiv:2605.18867v1 Announce Type: cross Abstract: Test-time model evolution offers a promising way for deployed models to improve from unlabeled test-time experience, yet most existing methods depend
arXiv:2605.18854v1 Announce Type: new Abstract: Coding agents accumulate extensive context during long-running tasks, yet fixed context windows force practitioners to choose between truncation and tas
arXiv:2605.18937v1 Announce Type: new Abstract: Patient-managed Personal Health Records (PHRs) promises to empower patients to better understand their health; but information in the record is complex,
arXiv:2605.19506v1 Announce Type: new Abstract: First-person dynamic spatial reasoning requires models to track continuous motion and precise geometric structure, but the quadratic attention cost of T
arXiv:2605.19283v1 Announce Type: cross Abstract: Sequential prediction is challenging in regimes of delayed disambiguation, where early observations are ambiguous and multiple latent explanations rem
Search startup Exa Labs Inc. today announced that it has raised 250 million in funding to purchase more infrastructure. The round was led by Andersen Horowitz. It comes less than a year after Exa’s pr
arXiv:2605.18848v1 Announce Type: cross Abstract: This paper introduces Exact Linear Attention (ELA), a mechanism that achieves linear computational complexity for Transformer attention by leveraging
Except the humans know that the Minds are smarter & they are content to leave all the big decisions (Contact, Special Circumstances, etc) to the AIs so they can do whatever they want personally aside
Juicebox App Inc. today introduced a suite of autonomous recruiting agents that help hiring teams proactively identify and engage candidates across multiple open roles simultaneously, recommending pro
arXiv:2605.19258v1 Announce Type: cross Abstract: Deep learning has enabled ECG diagnostic models with strong performance in tasks such as arrhythmia classification and abnormality detection. However,
This post compares large-scale scientific infrastructure projects like space telescopes, particle accelerators, and interplanetary probes to 'rare token hunting,' suggesting they represent humanity's
arXiv:2605.19826v1 Announce Type: new Abstract: Operators of safety-critical industrial processes increasingly rely on digital twins to screen control interventions, but such simulators rarely carry c
arXiv:2605.19947v1 Announce Type: new Abstract: This work addresses the problem of learning directed acyclic graphs (DAGs) from nodal observations generated by a linear structural equation model. DAG
arXiv:2605.19321v1 Announce Type: cross Abstract: Large Language Model (LLM) alignment remains vulnerable to jailbreak attacks that elicit unsafe responses, motivating pre-model and post-model guards.
arXiv:2605.19478v1 Announce Type: cross Abstract: Existing ViT backdoor attacks based on backbone-overwriting full-tuning are computationally expensive and inflict performance degradation. This has fo
arXiv:2509.26464v2 Announce Type: replace Abstract: Self-preference is a fundamental feature of biological organisms. Since large language models (LLMs) lack sentience, they might be expected to avoid
arXiv:2605.19859v1 Announce Type: new Abstract: Vision-language models (VLMs) have rapidly evolved into general-purpose multimodal reasoners with strong zero-shot generalization. In this context, VLMs
arXiv:2605.19291v1 Announce Type: cross Abstract: Stochastic gradient descent (SGD) is a fundamental optimization algorithm widely used in modern machine learning. In this paper, we propose Factor-Aug
arXiv:2605.19111v1 Announce Type: cross Abstract: Existing text-to-image (T2I) evaluation metrics mainly assess whether generated images align with information explicitly stated in the prompt, but oft
SpaceX filed its S-1 IPO prospectus with the SEC, offering public disclosure of its finances ahead of its investor roadshow planned for June . This filing contains the first-ever publicly disclosed in
arXiv:2605.19786v1 Announce Type: new Abstract: 4D mesh generation has recently emerged as a powerful paradigm for recovering dynamic 3D structure from videos, but existing methods remain slow, comput
arXiv:2605.19916v1 Announce Type: cross Abstract: We introduce Contrastive FUSE, a fast and unified framework for scalable node representation learning in graphs with partially available pairwise node
arXiv:2605.18908v1 Announce Type: cross Abstract: Deep neural networks (DNNs) remain critically vulnerable to backdoor attacks. Existing post-training detectors often require clean or surrogate data,
arXiv:2512.08237v3 Announce Type: replace Abstract: The advancement of vision-only Bird's-Eye-View (BEV) perception, a core paradigm for cost-effective autonomous driving, is hindered by the long-stan
arXiv:2605.19842v1 Announce Type: new Abstract: We propose a scalable tensorization framework for neural network compression based on slice-wise feature distillation. Unlike conventional tensor decomp
arXiv:2410.15362v2 Announce Type: replace-cross Abstract: Aligned Large Language Models (LLMs) have attracted significant attention for their safety, particularly in the context of jailbreak attacks t
arXiv:2509.14968v3 Announce Type: replace Abstract: The upcoming generations of wireless technologies promise an era where everything is interconnected and intelligent. As the need for intelligence gr
arXiv:2601.16200v3 Announce Type: replace-cross Abstract: Modern deep learning models exhibit strong capabilities across diverse applications, yet remain vulnerable to malicious inputs that induce err
arXiv:2605.18789v1 Announce Type: cross Abstract: Features in language models have life history: they emerge, persist, and die during training, yet the importance of that history remains largely unexp
arXiv:2601.01901v2 Announce Type: replace Abstract: Data-free knowledge distillation-based one-shot federated learning (OSFL) trains a model in a single communication round without sharing raw data, m
arXiv:2507.03122v2 Announce Type: replace-cross Abstract: This study investigates the feasibility and performance of federated learning (FL) for multi-label ICD code classification using clinical note
arXiv:2310.11203v2 Announce Type: replace Abstract: We introduce a novel strategy to train randomised predictors in federated learning, where each node of the network aims at preserving its privacy by
arXiv:2605.18936v1 Announce Type: cross Abstract: Social media text data are often used to train Machine Learning (ML) models to identify users exhibiting high-risk mental health behaviors. However, s
arXiv:2605.19949v1 Announce Type: new Abstract: Reconstructing large-scale urban scenes from sparse aerial views is a crucial yet challenging task. Due to biased top-down and shallow-oblique camera po
arXiv:2605.20016v1 Announce Type: cross Abstract: Short-form video poses new challenges to the quality assessment of user-generated content (UGC) due to its complex generation pipeline, rapid content
arXiv:2510.03589v2 Announce Type: replace Abstract: Spatio-temporal sensor data in real-world systems is often sparse, noisy, and irregular, making latent field reconstruction fundamentally underconst
Figured it out Personal update: I've joined Anthropic. I think the next few years at the frontier of LLMs will be especially formative. I am very excited to join the team here and get back to R&D. I r
arXiv:2605.20132v1 Announce Type: cross Abstract: Distributed acoustic sensing (DAS) systems generate continuous, ultra-high-channel-count data streams at rates that exceed the capabilities of convent
Financial analysts spend ~70% of their time pulling numbers out of PDFs. We built a demo agent that ingests SEC filings and answers questions with exact citations highlighted on the original PDF page.
arXiv:2602.04555v2 Announce Type: replace Abstract: Learning from a stream of tasks usually pits plasticity against stability: acquiring new knowledge often causes catastrophic forgetting of past info
arXiv:2605.18824v1 Announce Type: cross Abstract: Evaluation of foundation models often rely on aggregate scores from benchmarks that lack comprehensive coverage and metadata for a fine-grained evalua
Fine-tuned a distilbert with ml-intern today for the first time. The procedure is really straightforward, almost unexpectedly so. - Found a few datasets relevant to the task (prompt injection detectio
arXiv:2605.19224v1 Announce Type: new Abstract: Neuroscientists have recently turned to intracranial brain recording methods, like electrocorticography (ECoG), for human experiments because of the fin
arXiv:2507.10614v2 Announce Type: replace-cross Abstract: The integration of large language models (LLMs) into automated algorithm design has shown promising potential. A prevalent approach embeds LLM
arXiv:2605.20005v1 Announce Type: new Abstract: Fine-tuning large language models on new data improves task performance but degrades capabilities learned during pretraining, a phenomenon known as cata
arXiv:2605.19846v1 Announce Type: cross Abstract: Vision-Language Models (VLMs) have demonstrated remarkable capabilities in general video understanding, yet they often struggle with the fine-grained
arXiv:2509.25448v3 Announce Type: replace-cross Abstract: Large language models (LLMs) are often modified after release through post-processing such as post-training or quantization, which makes it ch
Fireworks is coming to Tech Week First up: Boston. We're co-hosting a rooftop founder social with @fin_ai and @TrustVanta — curated crowd, real conversations, limited space. Thu May 28 · 7–10pm · #BOS