Knowledge catalogue
arXiv:2602.09514v3 Announce Type: replace-cross Abstract: Long-horizon planning is widely recognized as a core capability of autonomous LLM-based agents; however, current evaluation frameworks suffer
arXiv:2506.08136v3 Announce Type: replace Abstract: We introduce EconWebArena, a benchmark for evaluating autonomous agents on complex, multimodal economic tasks in realistic web environments. The ben
arXiv:2605.06644v2 Announce Type: replace Abstract: Fluorescent protein quantum yield (QY) is governed by the mature chromophore and its three-dimensional microenvironment rather than sequence identit
arXiv:2605.08636v1 Announce Type: new Abstract: Federated fine-tuning offers a promising paradigm for adapting large language models (LLMs) on edge devices by leveraging the rich, diverse, and continu
arXiv:2605.09378v1 Announce Type: cross Abstract: Long-horizon video generation has advanced in visual quality, yet existing methods still struggle to maintain knowledge consistency and coherent pedag
arXiv:2605.09588v1 Announce Type: cross Abstract: Organizations increasingly deploy multiple AI systems across task domains, but selecting a small, high-performing ensemble can require costly model ca
arXiv:2601.20251v3 Announce Type: replace-cross Abstract: Exhaustively evaluating many large language models (LLMs) on a large suite of benchmarks is expensive. We cast benchmarking as finite-populati
arXiv:2605.09848v1 Announce Type: new Abstract: Electrocardiogram (ECG) interpretation is essential for diagnosing a wide range of cardiac abnormalities. While deep learning has shown strong potential
arXiv:2605.09874v1 Announce Type: cross Abstract: Next-generation visual assistants, such as smart glasses, embodied agents, and always-on life-logging systems, must reason over an entire day or more
arXiv:2605.10332v1 Announce Type: new Abstract: Embodied agents can benefit from skills that guide object search, action execution, and state changes across diverse environments. Since embodied enviro
arXiv:2605.08847v1 Announce Type: new Abstract: In the context of today's high-pressure, aging society, the demand for large-scale emotional models capable of providing empathetic support is more crit
arXiv:2605.09826v1 Announce Type: new Abstract: Theory of Mind (ToM), the ability to track others epistemic state, makes humans efficient collaborators. AI agents need the same capacity in multi agent
arXiv:2605.10556v1 Announce Type: new Abstract: As large language models span dense, mixture-of-experts, and state-space architectures and are deployed on heterogeneous accelerators under increasingly
arXiv:2605.09505v1 Announce Type: new Abstract: Epilepsy diagnosis and treatment require evidence-intensive reasoning across heterogeneous clinical knowledge, including biosignal patterns, genetic mec
arXiv:2605.10410v1 Announce Type: new Abstract: Large language models can score well on named game-theory benchmarks while failing on the same strategic computation once semantic cues are removed. We
arXiv:2505.22919v3 Announce Type: replace Abstract: Existing benchmarks for evaluating the clinical reasoning capabilities of large language models (LLMs) often lack a clear definition of 'clinical re
arXiv:2602.08617v2 Announce Type: replace Abstract: Scaling Federated Learning (FL) to billion-parameter models forces a challenging trade-off between privacy, scalability, and model utility. Existing
Even @haider1 sees that Mythos has been overhyped. mythos is pretty on par with gpt-5.5 and while gpt-5.5 is currently SOTA, it's not anything like what anthropic describes mythos as it's pretty obvio
arXiv:2510.06371v2 Announce Type: replace-cross Abstract: Large-scale multimodal models achieve strong results on tasks like Visual Question Answering (VQA), but they are often limited when queries re
arXiv:2605.08285v1 Announce Type: new Abstract: Autoregressive scientific forecasters often enforce physical or structural constraints by repairing each predicted state before feeding it back into the
arXiv:2605.08671v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly deployed not only to make decisions but to explain them. While AI decision fairness has been studied ext
arXiv:2509.13332v2 Announce Type: replace Abstract: As Large Language Models (LLMs) are increasingly adopted as automated judges in benchmarking and reward modeling, ensuring their reliability, effici
arXiv:2605.09773v1 Announce Type: cross Abstract: We use sparse autoencoder (SAE) feature steering to amplify Dark Triad personality traits (Machiavellianism, narcissism, and psychopathy) in Llama-3.3
arXiv:2603.00166v2 Announce Type: replace-cross Abstract: Recent advances in generative AI have shown human-level performance in complex content creation. However, we identify a 'Paradox of Simplicity
arXiv:2605.09923v1 Announce Type: new Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) has become the standard paradigm for LLM mathematical reasoning, where Group Relative Policy Optim
arXiv:2605.09081v1 Announce Type: cross Abstract: We introduce the first universal pretraining corpus for industrial time-series data: FactoryNet. 51M datapoints across 23k end-to-end task executions
arXiv:2605.08434v1 Announce Type: new Abstract: Vision-language-action (VLA) models provide a promising paradigm for scalable robotic manipulation, yet their reliance on success-only behavioral clonin
SpaceX's Falcon 9 rocket successfully launched the NROL-172 classified national reconnaissance payload from Space Launch Complex 4E at Vandenberg Space Force Base in California. This mission was condu
arXiv:2605.09827v1 Announce Type: cross Abstract: We present Fashion Florence, a Florence-2 vision-language model fine-tuned with LoRA to extract structured fashion attributes from clothing images. Gi
arXiv:2605.10127v1 Announce Type: new Abstract: Recent research work on fashion outfit generation focuses on promoting visual consistency of garments by leveraging key information from reference image
Cursor has released fast mode for Claude Opus 4.7, offering 2.5x faster processing speeds but at 6x the cost compared to standard mode. The announcement suggests that for most tasks, standard mode rem
Anthropic has released a fast mode for Claude Opus 4.7, now available in research preview for both the API and Claude Code, offering improved performance for compatible workloads. This feature allows
arXiv:2605.08119v1 Announce Type: cross Abstract: Tian (2025) proves a repulsion theorem (Theorem 6) for the matrix B = (widetilde{F}^op widetilde{F} + eta I)^{-1} during the interactive feature-learn
arXiv:2605.08149v1 Announce Type: cross Abstract: Sparse Autoencoders (SAEs) decompose large language model representations into interpretable features, but how these features interact under uncertain
arXiv:2603.16231v2 Announce Type: replace-cross Abstract: Numerical optimal control has long been split between globally structured but dimensionally intractable Hamilton--Jacobi--Bellman (HJB) method
arXiv:2605.09986v1 Announce Type: cross Abstract: Training a language model on data scattered across bandwidth-limited nodes that cannot be centralized is a setting that arises in clinical networks, e
arXiv:2605.10439v1 Announce Type: new Abstract: Low-Rank Adaptation (LoRA) has become a widely used mechanism for customizing diffusion models, enabling users to inject new visual concepts or styles t
arXiv:2605.09106v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly deployed in financial contexts, raising critical concerns about reliability, alignment, and susceptibility
arXiv:2502.18834v2 Announce Type: replace-cross Abstract: Financial time series (FinTS) record the behavior of human-brain-augmented decision-making, capturing valuable historical information that can
arXiv:2605.08657v1 Announce Type: cross Abstract: We study learnable logic gate networks that stack layers of 2-input Boolean gates to build combinational circuits. Every 2-input gate has a unique mul
arXiv:2605.10183v1 Announce Type: new Abstract: Sharpness-Aware Minimization (SAM) improves generalization by minimizing the worst-case loss within a fixed parameter-space radius neighborhood. SAM and
arXiv:2605.09355v1 Announce Type: new Abstract: Real-world model deployment across multiple domains requires multimodal models to operate under two complementary regimes: (1) multi-task pretraining, t
arXiv:2605.09218v1 Announce Type: cross Abstract: 3D scene understanding spans reasoning about free space, object grounding, hypothetical object insertions, complex geometric relationships, and integr
arXiv:2605.09003v1 Announce Type: new Abstract: Recently, diffusion-based object removal models have achieved impressive results in eliminating objects and their associated visual effects. However, th
arXiv:2605.10302v1 Announce Type: new Abstract: Existing approaches to controllable generation typically rely on fine-tuning, auxiliary networks, or test-time search. We show that flow matching admits
arXiv:2605.08905v1 Announce Type: new Abstract: Large Language Models (LLMs) have achieved remarkable success on reasoning benchmarks through Reinforcement Learning with Verifiable Rewards (RLVR), exc
arXiv:2605.10141v1 Announce Type: new Abstract: Recent neural theorem provers use reinforcement learning with verifiable rewards (RLVR), where proof assistants provide binary correctness signals. Whil
arXiv:2605.09163v1 Announce Type: new Abstract: Large language model agents increasingly operate through an intermediate skill layer that mediates between user intent and concrete task execution. This
arXiv:2512.02010v5 Announce Type: replace Abstract: As large language models have grown larger, interest has grown in low-precision numerical formats such as NVFP4 as a way to improve speed and reduce
arXiv:2605.09581v1 Announce Type: new Abstract: This paper presents a hardware architecture that implements the Contrast Maximization (CM) algorithm in Field-Programmable Gate Array (FPGA) resources f
arXiv:2605.08833v1 Announce Type: new Abstract: Effective sequence modeling fundamentally requires balancing the retention of unbounded history with the high-resolution detection of abrupt short-term
arXiv:2505.05406v2 Announce Type: replace Abstract: News headlines and summaries shape how events are interpreted through selective emphasis and omission, a phenomenon commonly referred to as framing.
arXiv:2605.08820v1 Announce Type: cross Abstract: Artificial Intelligence (AI)-generated images have become increasingly realistic and readily adaptable to concrete real-world claims, creating new cha
arXiv:2605.09664v1 Announce Type: cross Abstract: As over 200 million new malware samples are identified each year, antivirus systems must continuously adapt to the evolving threat landscape. However,
arXiv:2605.08712v1 Announce Type: new Abstract: Action-conditioned surgical video generation is a critical yet highly challenging problem for robotic surgery. The core difficulty is that low-dimension
arXiv:2605.09591v1 Announce Type: new Abstract: Segmentation is a fundamental vision task underlying numerous downstream applications. Recent promptable segmentation models, such as Segment Anything M
arXiv:2605.09147v1 Announce Type: cross Abstract: Part-of-speech (POS) tagging for Medieval Romance languages remains challenging due to orthographic variation, morphological complexity, and limited a
arXiv:2605.09356v1 Announce Type: new Abstract: Decentralized federated learning (FL) is a promising approach for training machine learning models on sensor networks, Internet of Things (IoT) devices,
arXiv:2605.09027v1 Announce Type: new Abstract: In multi-agent systems (MAS), a single deceptive agent can nullify all gains of an agentic AI collective and evade deployed defenses. However, existing
It is, once again, Gemini season. Google is announcing a host of new Gemini features during its pre-I/O Android showcase, many of which aim to help use your phone for you. You'll find Gemini in more p