Knowledge catalogue
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:2605.19478v1 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: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: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: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: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: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:2605.19846v1 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:2605.18845v1 Announce Type: cross Abstract: We give the first quantitative prediction of grokking delay under AdamW. Treating the delay as a first-passage time, we derive a closed-form law T_gro
arXiv:2605.18866v1 Announce Type: cross Abstract: Reconstructing continuous flow fields from sparse surface-mounted sensors is central to aerodynamic design, flow control, and digital-twin instrumenta
arXiv:2605.19812v1 Announce Type: cross Abstract: We introduce FLUXtrapolation, a benchmark for extrapolating ecosystem fluxes under progressively harder distribution shifts. Ecosystem fluxes are cent
for anyone curious, this was the result of many experiments bouncing around but this version uses... initial ideation: chatgpt for ideas/@replit for quick build final repo build: opus 4.7 prompting cl
For centuries, the scientific method has been our best tool for progress. But today, there’s so much data out there that it’s impossible for any one researcher to connect all the dots. We want to fix
Network verification company Forward Inc. today launched Forward Predict, a new capability that lets network teams test proposed changes against a digital twin of their production network before deplo
arXiv:2605.18860v1 Announce Type: cross Abstract: This paper proposes a neuron pruning framework based on neuron-level spectral structural importance evaluation. Given a trained neural network, we rec
arXiv:2605.19824v1 Announce Type: new Abstract: Recent attempts to support high-level scene interpretation and planning in Autonomous Vehicles (AVs) using ensembles of Large Language Models (LLMs) and
arXiv:2605.19781v1 Announce Type: new Abstract: Modern optimizers, like Muon, impose matrix-wise geometry constraints on their updates. These matrix-wise constraints can be unified under Linear Minimi
arXiv:2605.19263v1 Announce Type: new Abstract: Physics-informed neural networks (PINNs) offer a mesh-free framework for solving partial differential equations (PDEs), yet training often suffers from
arXiv:2605.18865v1 Announce Type: cross Abstract: Self-attention serves as the core foundation of large-scale transformer pretraining, but its quadratic token interaction cost makes inference expensiv
fun read on real tradeoffs & design decisions we debated when designing Engine for the data scale that customers produce one common thread is that we’re pretty strong supporters of just giving the age
Google introduced Gemini 3.5, its latest family of models combining frontier intelligence with action capabilities, representing a major leap forward in building more capable, intelligent agents. The
arXiv:2605.19813v1 Announce Type: new Abstract: We prove a general lower bound for differentially private federated learning protocols with arbitrary public-transcript interactions. The protocol may u
arXiv:2407.17200v3 Announce Type: replace-cross Abstract: Many real-world decision problems require solving, again and again, combinatorial optimization instances drawn from a common distribution. A r
arXiv:2605.20006v1 Announce Type: new Abstract: Geospatial reasoning requires solving image-grounded problems over the complex spatial structure of a scene. However, developing this capability is hind
arXiv:2605.19577v1 Announce Type: new Abstract: We present GoLongRL, a fully open-source, capability-oriented post-training recipe for long-context reinforcement learning with verifiable rewards (RLVR
It's hard to find much to write about Google I/O this year because I have a policy of not writing about anything that I can't try out myself, and a lot of the big announcements are 'coming soon'. I ac
Anu Adegbola / Search Engine Land: Google says it is testing new ad formats in search results and AI Mode, including Conversational Discovery ads, Highlighted Answers, and AI-powered Shopping ads — Go
Google's AI-powered Search era apparently also extends to its ads. Now, when you search for a product, Google's Gemini AI chatbot will surface relevant items and generate a 'custom explainer' about wh
Got to play with a little of this before launch as well. My experience as a social scientist was that it was more bioscience focused right now, but I think Google has been the leading lab in releasing
arXiv:2605.19890v1 Announce Type: new Abstract: Test-time adaptation (TTA) enables a pre-trained model to adapt online to an unlabeled test stream under distribution shift. While most TTA research foc
arXiv:2509.21698v2 Announce Type: replace Abstract: Risk categorization in 10-K risk disclosures matters for oversight and investment, yet no public benchmark evaluates unsupervised topic models for t
arXiv:2605.19733v1 Announce Type: cross Abstract: Community detection is a central problem in graph analysis, with applications ranging from network science to graph signal processing. In recent years
arXiv:2605.19765v1 Announce Type: new Abstract: Existing affective-computing, social-signal-processing, and meeting corpora capture important parts of human interaction, but they rarely support analys
arXiv:2605.19192v1 Announce Type: new Abstract: Multimodal agents use screenshots, documents, and webpages to choose tool calls. When a false visual claim triggers a click, email, extraction, or trans
arXiv:2605.19341v1 Announce Type: cross Abstract: Hallucination remains a central failure mode of large language models, but existing benchmarks operationalize it inconsistently across summarization,
arXiv:2605.19223v1 Announce Type: new Abstract: While Multimodal Large Language Models (MLLMs) exhibit strong performance on standard video tasks, their ability to faithfully summarize and reason over
arXiv:2605.18795v1 Announce Type: cross Abstract: Low-Rank Adaptation (LoRA) dominates parameter-efficient fine-tuning of large language models, yet most variants target dense architectures. Mixture-o
arXiv:2603.17839v3 Announce Type: replace-cross Abstract: Verbal confidence -- prompting LLMs to state their confidence as a number or category -- is widely used to extract uncertainty estimates from
arXiv:2605.18814v1 Announce Type: new Abstract: Trajectory-based data attribution methods estimate the influence of training samples on model predictions by unrolling the training trajectory. They are
arXiv:2605.19156v1 Announce Type: new Abstract: Recent auto-research systems can produce complete papers, but feasibility is not the same as quality, and the field still lacks a systematic study of ho
Ramp engineers use OpenAI's Codex to streamline and accelerate their code review process, leveraging AI-assisted code understanding and analysis. The implementation likely demonstrates how Codex helps
arXiv:2605.18822v1 Announce Type: cross Abstract: Post-training has become essential for adapting large language models (LLMs) to complex downstream behaviors, including instruction following, prefere
I am starting to have trouble paying attention to even interesting information if it is written in Claude or ChatGPT house style. I think some is the sameness of the rhythm rather than obvious tics: C
I don't have much to say about this year's Google I/O because I prefer to write about products that have shipped, not just 'coming soon' announcements - but here are some notes on Gemini Spark and Ant
i don't think i need cloud models anymore MTP speedup Qwen by 2.5x in Atomic Chat Dense vs MoE models on 2x RTX 5090 Qwen3.6 27B: 51 → 117 tps +137% Qwen3.6 35B-A3B: 218 → 267 tps +25% MTP drafts seve
arXiv:2605.19301v1 Announce Type: new Abstract: Vision-Language Models require efficient adaptation to continually emerging downstream tasks. While Parameter-Efficient Fine-Tuning mitigates catastroph
arXiv:2605.19346v1 Announce Type: cross Abstract: We present IMLJD, an open dataset of 3,613 Indian court judgments covering matrimonial disputes under IPC Section 498A, the Protection of Women from D
arXiv:2605.18830v1 Announce Type: new Abstract: Regression and Bayesian accounts of in-context learning (ICL) explain how demonstrations can induce predictors, while mechanistic analyses often identif
arXiv:2605.19152v1 Announce Type: cross Abstract: Physical computing systems provide a promising route toward hardware-native machine learning, but their computational capabilities remain difficult to
arXiv:2605.20088v1 Announce Type: cross Abstract: Discovering shapelets -- i.e., discriminative temporal patterns within time series -- has been widely studied to address the inherent complexity of ti
As models and harnesses improve, agents are taking on increasingly complex tasks that can run for hours or even days. But as we push agents to do more, this has surfaced a new operational problem: lon
Cohere announced Command A+, their most advanced large language model to date, designed with optimization for efficient hardware requirements to enable broader deployment and accessibility. The model
It's been *almost* a bit quiet around LLM architecture releases in the past two weeks 😅 Interesting tidbit is the parallel block design. Via the Cmd-A the tech report 'equivalent performance but signi
it’s in gemini, just create it in ai studio. oh, that’s for your personal google one account. for workspace you need gemini business. no, not gemini advanced, that’s ai pro now. unless you need ai ult
arXiv:2605.19926v1 Announce Type: new Abstract: The progression of reinforcement learning algorithms have been driven by challenging benchmarks. The rate in which a researcher can iterate on a problem
arXiv:2605.19645v1 Announce Type: new Abstract: Recent advancements in large language models (LLMs) have shown their remarkable capacities in many NLP tasks. However, their substantial size often pres