Knowledge catalogue
arXiv:2605.03562v1 Announce Type: new Abstract: KV-cache quantizers usually optimize storage-space reconstruction, even though attention reads keys through logits and values through attention-weighted
arXiv:2605.03252v1 Announce Type: cross Abstract: LoRA fine-tuning of diffusion transformers (DiT) on multi-style data suffers from style bleed: a single low-rank residual cannot represent several dis
arXiv:2605.01123v1 Announce Type: new Abstract: Large language models (LLMs) can provide automated feedback in educational settings, but aligning an LLMs style with a specific instructors tone while m
arXiv:2605.01280v1 Announce Type: cross Abstract: This position paper argues that LLM inference serving has outgrown generic heuristics and now demands mathematical optimization and algorithmic founda
arXiv:2605.03999v1 Announce Type: new Abstract: Vision Transformers (ViTs) achieve state-of-the-art segmentation accuracy but require large training datasets because each layer has unique parameters t
arXiv:2605.03258v1 Announce Type: cross Abstract: Large language models often fail at simple counting tasks, even when the items to count are explicitly present in the prompt. We investigate whether t
The AI era demands a fundamental shift in security, and that includes identity and access management (IAM). Traditional controls simply aren’t built for autonomous AI agents that interact with sensiti
arXiv:2605.03609v1 Announce Type: cross Abstract: Large language models often display heterogeneous moral preferences across settings. We study inference-time steering toward a desired ethical framewo
arXiv:2507.04441v4 Announce Type: replace-cross Abstract: Conformal prediction (CP) produces prediction regions with finite-sample, distribution free coverage guarantees, but its interpretation as a q
arXiv:2605.00236v1 Announce Type: cross Abstract: Safety-aligned large language models rely on RLHF and instruction tuning to refuse harmful requests, yet the internal mechanisms implementing safety b
arXiv:2601.12024v2 Announce Type: replace-cross Abstract: Customer reviews contain valuable signals about service quality, but converting large-scale review corpora into actionable business recommenda
arXiv:2605.02348v1 Announce Type: new Abstract: Large language models pick up social biases from the data they are trained on and carry those biases into downstream applications, often reinforcing ste
arXiv:2605.01848v1 Announce Type: new Abstract: Synthesizing longitudinal medical images at controllable disease stages while preserving patient-specific anatomy is hindered by the entanglement of pat
arXiv:2605.01929v1 Announce Type: new Abstract: Video diffusion models leveraging step distillation or causal distillation have achieved remarkable performance. However, adapting existing LoRAs to the
Building AI agents that work well in a demo is one thing, but running them in production requires serious infrastructure. At Google Cloud Next '26, we introduced Gemini Enterprise Agent Platform to he
arXiv:2505.14062v3 Announce Type: replace Abstract: Vision Mamba offers linear complexity for long visual sequences, yet its performance depends critically on how a two-dimensional patch grid is seria
arXiv:2605.01656v1 Announce Type: cross Abstract: Human cognition emerges from coordinated spiking dynamics in distributed neural circuits, where information is encoded via both firing rates and preci
arXiv:2605.02814v1 Announce Type: new Abstract: Blind face restoration is highly ill-posed under severe degradation, where identity-critical details may be missing from the degraded input. Same-identi
Managing agents and their actions can quickly grow in complexity and introduce security risks unique to AI. To address these challenges, at Google Cloud Next we announced Agent Gateway to provide simp
arXiv:2605.02641v1 Announce Type: new Abstract: We present Mamoda2.5, a unified AR-Diffusion framework that seamlessly integrates multimodal understanding and generation within a single architecture.
arXiv:2605.01580v1 Announce Type: new Abstract: Modern deep learning usually treats models as separate artifacts: trained independently, specialized for particular purposes, and replaced when improved
arXiv:2605.02509v1 Announce Type: new Abstract: Continual learning systems face a fundamental tension between plasticity -- acquiring new knowledge -- and stability -- retaining prior knowledge. We in
arXiv:2605.02437v1 Announce Type: new Abstract: Objective: Accurate probability estimates are essential for the safe deployment of medical image segmentation models in clinical decision-making. Howeve
arXiv:2605.02447v1 Announce Type: new Abstract: Multimodal sarcasm detection, which aims to precisely identify pragmatic incongruities between literal text and nonverbal cues, has gained substantial a
arXiv:2605.00915v1 Announce Type: new Abstract: Standard representation probing for visual models relies on mathematically permutation-invariant operations like Global Average Pooling (GAP) or CLS tok
arXiv:2605.00515v1 Announce Type: cross Abstract: Leveraging continuous solar energy harvesting at high efficiency, space data centers are envisioned as a promising platform for executing energy-inten
arXiv:2604.07421v2 Announce Type: replace Abstract: Full-waveform inversion (FWI) is pivotal for reconstructing high-resolution subsurface velocity models but remains computationally intensive and ill
arXiv:2601.20055v2 Announce Type: replace Abstract: Despite the syntactic fluency of Large Language Models (LLMs), ensuring their logical correctness in high-stakes domains remains a fundamental chall
arXiv:2605.02735v1 Announce Type: new Abstract: Continuous latent-space reasoning offers a compact alternative to textual chain-of-thought for multimodal models, enabling high-dimensional visual evide
arXiv:2605.00410v1 Announce Type: new Abstract: A multi-agent pipeline with N agents typically issues N LLM calls per run. Merging agents into fewer calls (compound execution) promises token savings,
arXiv:2605.00334v1 Announce Type: cross Abstract: Production agentic systems make many model calls per user request, and most of those calls are short, structured, and routine. This raises a practical
arXiv:2605.00083v1 Announce Type: new Abstract: Accurate forecasting of bus ridership (passengers numbers) is crucial for efficient management and optimization of public transport systems. Traditional
fleet is built on top of deepagents, a model agnostic base harness! try building multi-model agents in fleet today, or build your own deep agent with the underlying sdk! Not every step in an agent wor
arXiv:2605.00474v1 Announce Type: new Abstract: Modern vision models achieve remarkable accuracy, but explaining where evidence arises, what the model encodes, and how internal computations assemble t
arXiv:2605.00799v1 Announce Type: new Abstract: Gaze estimation methods commonly use facial appearances to predict the direction of a person gaze. However, previous studies show three major challenges
arXiv:2605.00351v1 Announce Type: new Abstract: Root cause localization in cloud native microservice systems requires modeling complex service dependencies, irregular temporal dynamics, and heterogene
NEW paper from Sakana AI (ICLR 2026). A 7B Conductor model just hit SOTA on GPQA-Diamond and LiveCodeBench by orchestrating other LLMs instead of solving problems itself. (great paper! bookmark it!) T
No longer are Fleet agents constrained to a single model. With multi-model support, you can build more efficient agents at scale http://langchain.com/langsmith/fleet Not every step in an agent workflo
arXiv:2605.00193v1 Announce Type: new Abstract: Many machine learning systems make constrained decisions by optimizing factorized objectives, but the context-specific objective is often treated as fix
arXiv:2605.00384v1 Announce Type: new Abstract: Preference-based reinforcement learning offers a scalable alternative to manual reward engineering by learning reward structures from comparative feedba
arXiv:2605.00099v1 Announce Type: cross Abstract: Despite rapid recent advances in quantum machine learning, the field is in many ways stuck. Existing approaches can exhibit serious limitations, and w
arXiv:2604.07669v2 Announce Type: replace Abstract: Lead optimization in drug discovery requires improving therapeutic properties while ensuring that molecular modifications correspond to feasible syn
arXiv:2605.00528v1 Announce Type: cross Abstract: AI agents execute tens to hundreds of chained LLM calls per task, yet GPU schedulers treat each call as independent, discarding gigabytes of intermedi
arXiv:2605.00402v1 Announce Type: cross Abstract: Spiking Neural Networks (SNNs) provide a promising framework for energy-efficient and biologically grounded computation; however, scalable learning in
The year of the harness 🤝 Harnesses are our most direct layer to turn a model into a great product experience for users by shaping model behavior towards a goal This matters today because models have
arXiv:2604.26999v1 Announce Type: new Abstract: Physics-informed neural networks (PINNs) approximate solutions of partial differential equations (PDEs) by embedding physical laws into the loss functio
arXiv:2604.28011v1 Announce Type: new Abstract: Ultrasound interpretation requires both precise lesion localization and holistic clinical reasoning, yet existing methods typically excel at only one of
arXiv:2602.00095v3 Announce Type: replace-cross Abstract: Multimodal Large Language Models (MLLMs) hold significant promise for revolutionizing traditional education and reducing teachers' workload. H
arXiv:2604.27092v1 Announce Type: new Abstract: Scientific research has long been human-led, driving new knowledge and transformative technologies through the continual revision of questions, methods
arXiv:2510.05192v2 Announce Type: replace-cross Abstract: When AI agents operating with access to sensitive information encounter a conflict between completing an assigned task and following rules or
arXiv:2604.27891v1 Announce Type: new Abstract: Agent orchestration frameworks -- LangGraph, CrewAI, Google ADK, OpenAI Agents SDK, and others -- place an external orchestrator above the LLM, tracking
arXiv:2604.27599v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used for recommendation reranking, but their listwise predictions can depend on the order in which candi
arXiv:2604.27401v1 Announce Type: new Abstract: Perturbation probing generates task-specific causal hypotheses for FFN neurons in large language models using two forward passes per prompt and no backp
arXiv:2512.23192v3 Announce Type: replace Abstract: While Transformers have demonstrated remarkable potential in modeling Partial Differential Equations (PDEs), modeling large-scale unstructured meshe
arXiv:2601.08418v2 Announce Type: replace-cross Abstract: Tax code prediction is a crucial yet underexplored task in automating invoicing and compliance management for large-scale e-commerce platforms
arXiv:2604.27256v1 Announce Type: cross Abstract: We present extsc{dm-PhiSNet}, a physically constrained extsc{PhiSNet}-based equivariant model that predicts one-electron reduced density matrices (1-R
arXiv:2604.27586v1 Announce Type: new Abstract: Reasoning over heterogeneous artifacts (PDFs, spreadsheets, slide decks, etc.) increasingly occurs within structured agent workflows that iteratively ex
arXiv:2604.26807v1 Announce Type: new Abstract: Despite being resource-intensive to train, 3D convolutional neural networks (CNNs) have been the standard approach to classify CT and MRI scans. Recent
arXiv:2603.25980v2 Announce Type: replace-cross Abstract: Transition states, the first-order saddle points on the potential energy surfaces, govern the kinetics and mechanisms of chemical reactions an
arXiv:2603.16496v2 Announce Type: replace Abstract: Large language model (LLM) agents increasingly rely on external memory to support long-horizon interaction, personalized assistance, and multi-step