Knowledge catalogue
arXiv:2606.08953v1 Announce Type: new Abstract: Modern generative models often define an entire probability path from a simple prior to the data law, rather than only an endpoint map. Diffusion models
arXiv:2606.07963v1 Announce Type: new Abstract: Backdoor attacks in large language models (LLMs) are often treated as isolated trigger-response failures, motivating defenses tailored to specific trigg
arXiv:2606.08236v1 Announce Type: cross Abstract: As large language models are increasingly deployed in high-stakes settings, there is a growing need for tools that audit not only model outputs but al
arXiv:2606.09213v1 Announce Type: cross Abstract: Spiking neural networks (SNNs) are increasingly trained in a wide range of frameworks (SnnTorch, Lava, Norse, and others) each with its own model form
Cohere advocates for democratizing access to sovereign AI systems, enabling organizations and nations to develop and deploy their own AI models independently rather than relying on centralized provide
arXiv:2606.08635v1 Announce Type: new Abstract: Prefill-decode (PD) disaggregation decouples prompt processing from token generation, but it also turns the key-value (KV) cache into a network payload.
arXiv:2606.09135v1 Announce Type: cross Abstract: We demonstrate that widely deployed Large Language Model (LLM) inference stacks harbor a steganographic channel that requires no modification to model
arXiv:2606.07689v1 Announce Type: new Abstract: Deep research agents have attracted increasing attention for their ability to collect large-scale online information to acquire target knowledge, with r
arXiv:2606.09204v1 Announce Type: new Abstract: We present a reproducible failure mode of safety training in RAG-based LLM recommendation -- the Injection Paradox -- in which prompt injections embedde
arXiv:2402.08922v3 Announce Type: replace Abstract: Large-scale black-box models have become ubiquitous across numerous applications. Understanding the influence of individual training data sources on
There has been a lot of hand wringing on the appropriate valuation of SpaceX. Some large institutions believe SpaceX can only be valued at half what the market seems to be willing to pay for it. Other
arXiv:2411.19504v2 Announce Type: replace Abstract: The advance of large language models (LLMs) has unlocked great opportunities in complex multi-modal data management tasks, particularly in question
arXiv:2606.09323v1 Announce Type: new Abstract: Tabular encoders are usually evaluated inside task-specific end-to-end pipelines, so models from different training paradigms are difficult to compare d
arXiv:2606.07953v1 Announce Type: new Abstract: Large-scale Visual-Language Models (LVLMs) have achieved remarkable success in natural visual tasks, yet their application to industrial defect detectio
arXiv:2606.08018v1 Announce Type: new Abstract: Existing text-to-SQL benchmarks are largely centered on SQLite, making it difficult to evaluate whether models can generalize across heterogeneous SQL d
arXiv:2510.03244v2 Announce Type: replace-cross Abstract: Large time series foundation models often adopt channel-independent architectures to handle varying data dimensions, but this design ignores c
We've got 13 days to burn as much tokens as humanly possible on Claude Max plans Before they revert to API based billing 💀 Introducing Claude Fable 5: a Mythos-class model that we’ve made safe for gen
arXiv:2606.06505v1 Announce Type: cross Abstract: We introduce a user defined probabilistic polygonal representation for plane curves. Given a curve, we select vertices on the curve and connect consec
arXiv:2606.07462v1 Announce Type: new Abstract: As foundation models advance and agent scaffolding becomes increasingly sophisticated, agents have demonstrated remarkable proficiency in complex, long-
arXiv:2606.06924v1 Announce Type: new Abstract: Existing LLM routing methods typically treat a model's single response to a query as its capability label for training routers. However, because LLM gen
arXiv:2606.07239v1 Announce Type: new Abstract: The success of generative molecular design hinges on a model's steerability toward high-reward samples. Because many molecular properties are intrinsica
arXiv:2606.07316v1 Announce Type: cross Abstract: Byzantine collaboration among large-language-model agents requires a finality-control primitive: given delivered stochastic, structured natural-langua
arXiv:2606.07033v1 Announce Type: new Abstract: Open-vocabulary audio-visual event localization (OV-AVEL) jointly models audio-visual cues to recognize and temporally localize events, including catego
arXiv:2606.06586v1 Announce Type: new Abstract: Large language models (LLMs) trained predominantly on English data encode substantial world knowledge, yet often fail to express it reliably in other la
arXiv:2512.23128v2 Announce Type: replace-cross Abstract: Web-based agents powered by large language models are increasingly used for tasks such as email management or professional networking. Their r
arXiv:2606.07512v1 Announce Type: cross Abstract: Current Vision-Language Models struggle with hours-long videos because processing full-length visual sequences induces prohibitive token explosion and
arXiv:2606.07392v1 Announce Type: new Abstract: Motivated by Large Language Model (LLM) cascading, we propose an online contextual Pandora's Box model for adaptively querying and selecting LLM APIs. I
arXiv:2606.06755v1 Announce Type: new Abstract: Authorship attribution research has traditionally focused on long-form, expressive texts; however, interactions with large language models (LLMs) are ty
arXiv:2606.06497v1 Announce Type: cross Abstract: Generative video models have achieved remarkable visual fidelity, yet their prompt-only interface offers thin creative agency and obscures the model's
arXiv:2606.07141v1 Announce Type: cross Abstract: Language models trained for clinical disease inference are trained on patient data, which may include sensitive and private information, and data owne
arXiv:2606.07181v1 Announce Type: cross Abstract: Single-step retrosynthesis needs both accurate first-ranked suggestions and candidate lists that are rich enough for downstream selection. We study th
arXiv:2604.07472v2 Announce Type: replace Abstract: Serving large language model (LLM) inference in cloud environments requires jointly optimizing model selection, GPU provisioning, parallelism config
arXiv:2606.07175v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) have raised new privacy challenges. On the data side, user-provided inputs often include unpredictable sensitiv
arXiv:2606.07098v1 Announce Type: new Abstract: We present SigmaScale, a method for learning auxiliary scaling matrices S to aid truncated Singular Value Decomposition (SVD) based Large Language Model
arXiv:2606.07036v1 Announce Type: cross Abstract: Synthetic histopathology image generation addresses critical challenges in computational pathology, including patient privacy and the growing need for
arXiv:2606.07451v1 Announce Type: cross Abstract: Vision-language models such as CLIP are highly useful for diverse tasks due to their shared image-text embedding space. Despite this, the image and te
arXiv:2606.07338v1 Announce Type: new Abstract: Vision-language driving models increasingly use reasoning supervision to bridge perception, prediction, and planning, but existing driving rationales ar
arXiv:2606.07171v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) enable flexible instruction-driven image editing, but privacy risks arise when user images expose diverse and u
arXiv:2606.05682v1 Announce Type: new Abstract: Demand for low-precision inference, including NVFP4-based approaches, has grown as large language models are increasingly deployed in latency and cost c
arXiv:2606.06212v1 Announce Type: new Abstract: Misconfigurations in computer networks remain a major source of critical Internet outages. Research is turning to Large Language Models (LLMs) to automa
arXiv:2606.05187v1 Announce Type: cross Abstract: Among the many challenges hindering the responsible development and deployment of AI, arguably none has faced more intense scrutiny than bias in its v
arXiv:2606.05566v1 Announce Type: new Abstract: Large Language Models (LLMs) have transformed natural language processing, but they remain vulnerable to Prompt Injection (PI) and Jailbreak (JB) attack
arXiv:2606.05613v1 Announce Type: new Abstract: The rapid evolution of Large Language Models (LLMs) has established cross-lingual versatility as a defining feature of modern systems. However, fine-tun
arXiv:2606.05555v1 Announce Type: cross Abstract: Scaling reinforcement learning (RL) to diverse multitask settings remains a central challenge. While recent advances in model-based RL achieve strong
arXiv:2606.05342v1 Announce Type: new Abstract: AI agents are increasingly asked to carry out work that spans minutes, hours, or longer. Yet the default model of agent behavior is continuous action: i
arXiv:2606.06333v1 Announce Type: cross Abstract: Sparse Autoencoders (SAEs) are widely used for mechanistic interpretability in large language models, yet their formulation assigns each latent featur
arXiv:2606.06337v1 Announce Type: new Abstract: Large language model (LLM) deployments for long-horizon tasks face a fundamental constraint: context windows are finite while productive work sessions a
arXiv:2606.06284v1 Announce Type: new Abstract: Large language model agents increasingly rely on external tools, but larger tool menus can reduce reliability and efficiency by increasing wrong-tool ca
arXiv:2606.06453v1 Announce Type: new Abstract: Sparse attention is becoming increasingly important for serving large language models (LLMs) as generation lengths continue to grow. However, deploying
arXiv:2606.06055v1 Announce Type: new Abstract: Long-term memory enables language model agents to support personalized interactions, but it remains unclear when available memories warrant integration
Arena AI's agentic benchmark ranks AI models on how well they orchestrate tools for real-world agentic tasks, based on signals like tool reliability, task completion, and steerability. The leaderboard
At least until (if?) rapid improvement stops, it seems less likely someone is going to catch the Big Three AI Labs. Microsoft and Meta released their models, which were fine, but not frontier. SpaceX
arXiv:2606.06219v1 Announce Type: new Abstract: End-to-end autonomous driving models often struggle to balance multi-modal maneuver generation with real-time inference constraints. While diffusion mod
arXiv:2606.05793v1 Announce Type: new Abstract: While LLM-based agents excel at individual tasks, effective collaboration with realistic human partners remains challenging. Most of the existing conver
arXiv:2508.15851v2 Announce Type: replace Abstract: Despite rapid progress in large language models (LLMs), current QA benchmarks still overlook the core challenge of real-world scientific information
arXiv:2606.05471v1 Announce Type: new Abstract: Learning semantics is essential for deep learning models to be interpretable and better aligned with human reasoning. Concept-based models approach this
arXiv:2606.06266v1 Announce Type: new Abstract: Hate speech detection is inherently subjective: people from different demographic groups perceive the same content very differently. Collecting enough a
arXiv:2606.05175v1 Announce Type: new Abstract: We study generic triple-latent sequence models that maintain a running token state and compressed pair-memory pathway to capture higher-order token inte
Gemma4 is a language model available through Ollama's model library with multiple tagged versions for different use cases and configurations. The Ollama platform enables users to run open-source large
arXiv:2606.06044v1 Announce Type: new Abstract: Retrieval-Augmented Generation (RAG) has shown strong effectiveness in grounding Large Language Models (LLMs) with external knowledge. However, existing