Knowledge catalogue
We raised $8m to build self-healing software. In 2026, software moves fast. But monitoring and observability are still manual and slow. @sazabi is a next-generation observability platform for fast-mov
arXiv:2606.25182v1 Announce Type: new Abstract: Jailbreak attacks reveal a persistent weakness in aligned Large Language Models: carefully crafted prompts can elicit policy-violating responses despite
arXiv:2606.24510v1 Announce Type: new Abstract: Rare diseases affect millions of individuals worldwide, yet timely diagnosis remains a major public health challenge due to scarcity of specialized clin
arXiv:2606.24143v1 Announce Type: new Abstract: On-policy distillation (OPD) trains a student on its own rollouts guided by teacher feedback and is becoming increasingly important for large language m
The search results do not contain specific information about the b9777 release. Based on the available information about llama.cpp releases, b9777 is an intermediate build release from the llama.cpp p
arXiv:2606.20146v3 Announce Type: replace Abstract: Large language models (LLMs) are increasingly applied to computer-aided design (CAD) to generate design artifacts from textual instructions. In engi
arXiv:2606.24740v1 Announce Type: new Abstract: Recent advances in vision-language models (VLMs) such as CLIP have demonstrated strong generalization across natural-image domains. However, adapting th
arXiv:2606.24752v1 Announce Type: new Abstract: The loss of plasticity - the ability of a network to learn new information after having already learned older information - is a fundamental challenge i
arXiv:2606.24758v1 Announce Type: new Abstract: Handling repeated characters in text can be tricky, since they can represent either the correct spelling of a word or informal character elongation ofte
arXiv:2606.24714v1 Announce Type: new Abstract: Chinese news text contains dense written forms such as scores, hyphenated model names, ranges, unit symbols, percentages, English abbreviations, and mix
arXiv:2602.14612v4 Announce Type: replace-cross Abstract: Answering natural-language questions over multi-hour audio requires both event recognition and temporal grounding. Current large audio-languag
arXiv:2511.13645v2 Announce Type: replace Abstract: Operational knowledge-graph (KG) pipelines in networking and cybersecurity increasingly need to refresh embeddings under strict time, memory, and au
arXiv:2606.24335v1 Announce Type: new Abstract: Counterfactual analysis is widely used to study evidence use in vision-language models, but its diagnostic value is limited on well-posed tasks: when se
arXiv:2606.24808v1 Announce Type: cross Abstract: Quantum computers could outperform classical machines on important problems, but only if the errors that pervade quantum hardware can be corrected at
arXiv:2606.19416v2 Announce Type: replace Abstract: Loan origination is the process by which a lender creates a new loan, from application and underwriting through approval and funding. This process s
arXiv:2606.24408v1 Announce Type: new Abstract: Assessing the privacy of large language models (LLMs) presents significant challenges. In particular, most existing methods for auditing differential pr
arXiv:2603.15510v2 Announce Type: replace Abstract: The synthesis of inductive loop invariants remains a critical bottleneck in automated program verification. While Large Language Models (LLMs) show
arXiv:2606.24381v1 Announce Type: cross Abstract: Prompt-based interaction has become a dominant paradigm for using large language models (LLMs), where multiple candidate prompts are evaluated and the
arXiv:2601.11957v4 Announce Type: replace Abstract: Overlapping calendar invitations force busy professionals to repeatedly decide which meetings to attend, reschedule, or decline. We refer to this pr
arXiv:2606.24346v1 Announce Type: cross Abstract: Petroleum-engineering search exposes a supervision gap for strong general retrievers: relevant evidence exists in public web text, but domain relevanc
arXiv:2606.24251v1 Announce Type: new Abstract: Large language models exhibit a growing range of misaligned behaviors such as strategic deception, sandbagging, and self-preservation. As they are incre
arXiv:2606.24496v1 Announce Type: cross Abstract: The use of agentic systems to perform offensive security operations has moved from a theoretical possibility to a commoditized capability. However, wh
arXiv:2606.23927v1 Announce Type: new Abstract: Agentic AI systems powered by large language models (LLMs) are rapidly evolving into autonomous decision-making systems, exposing attack vectors beyond
arXiv:2606.24626v1 Announce Type: new Abstract: As autonomous agents tackle increasingly complex multi-step, multi-agent tasks, their execution trajectories have scaled beyond the constraints of even
arXiv:2606.24477v1 Announce Type: cross Abstract: Video large language models (LLMs) are often constrained by computation and memory budgets, leading them to use reduced frame rates and spatial resolu
What is actually limiting model routers for coding tasks? Most routers treat picking a model as a static, one-off classification. This paper identifies the real bottleneck as information deficit. Simp
arXiv:2407.18957v5 Announce Type: replace-cross Abstract: Can AI Agents simulate real-world trading environments to investigate the impact of external factors on stock trading activities (e.g., macroe
arXiv:2606.24619v1 Announce Type: new Abstract: Competency Questions (CQs) are the central component of CQ-verification, an established process in which an ontology is evaluated against a set of natur
arXiv:2606.21257v1 Announce Type: new Abstract: OpenPangu models are attractive targets for private and domestic large-language-model deployment, yet their robustness under aggressive post-training qu
The search results do not contain specific details about the b9769 release. Based on the available information about llama.cpp and its release patterns, here is a knowledge base entry: Release b9769 o
Release b9773 of llama.cpp adds Vulkan support for the GET_ROWS_BACK operation . The release includes pre-built binaries for multiple platforms including macOS, Linux, Windows, and Android with variou
arXiv:2606.23494v1 Announce Type: new Abstract: Automated diagnosis of 3D brain CT scans is essential for critical care, yet it remains challenging due to the heavy reliance on manual annotations and
arXiv:2606.23157v1 Announce Type: new Abstract: This paper presents a modular training-free framework for zero-shot, language-guided robotic manipulation in semi-structured environments. The architect
arXiv:2606.22699v1 Announce Type: new Abstract: Frontier multimodal models can guess whether a person is lying from a testimony video. To do so, they stream that raw face and voice to a third-party mo
arXiv:2606.22000v1 Announce Type: cross Abstract: We introduce CFAgentBench, a reproducible, self-hostable environment and benchmark for autonomous construction-finance agents: a CFO/controller-class
arXiv:2606.20608v1 Announce Type: cross Abstract: Generative text-to-video systems can produce visually fluent educational clips, but they rarely encode the pedagogical content knowledge (PCK) needed
arXiv:2603.14837v2 Announce Type: replace Abstract: Analyzing street-view imagery with computer vision models offers a promising approach for rapid, hyperlocal disaster damage assessment, but existing
arXiv:2606.22918v1 Announce Type: new Abstract: Maintaining physical consistency in video generators and world models increasingly relies on vision-language models (VLMs) as automated judges that prov
arXiv:2606.22496v1 Announce Type: cross Abstract: Large language models (LLMs) offer a natural-language interface for interpreting Internet of Things (IoT) sensor data in smart environments; however,
arXiv:2602.21218v2 Announce Type: replace-cross Abstract: High-quality data is essential for modern machine learning, yet many valuable corpora are sensitive and cannot be freely shared. Synthetic dat
arXiv:2602.17431v2 Announce Type: replace-cross Abstract: Uncertainty quantification has emerged as an effective approach to closed-book hallucination detection for LLMs, but existing methods are larg
arXiv:2606.21993v1 Announce Type: cross Abstract: Autonomous vehicles (AVs) face driving scenarios ranging from routine traffic to rare events. To assess safety it is crucial to reproduce these scenar
arXiv:2606.23312v1 Announce Type: new Abstract: Operating in complex real-world environments requires robots to understand their surroundings on a functional semantic level. This demands a detailed mu
arXiv:2606.20707v1 Announce Type: new Abstract: While humans can identify physically implausible events within milliseconds, machine learning approaches addressing the same problem are extremely slow
arXiv:2606.23406v1 Announce Type: new Abstract: We present HyperQuant (Hadamard, optimallY Packing, Entropy Rice-coding), a unified post-training quantization pipeline for the weights and the KV cache
arXiv:2606.22841v1 Announce Type: cross Abstract: As Large Language Models (LLMs) achieve widespread integration across diverse linguistic landscapes, ensuring their safety and alignment with regional
To effectively operate and troubleshoot applications, developers and site reliability engineers (SREs) need to understand the full context of their system's behavior, typically as part of their loggin
arXiv:2606.21194v1 Announce Type: new Abstract: Medical Vision-Language Models (Med-VLMs) achieve strong expert-level performance, yet their ability to generate patient-accessible descriptions remains
arXiv:2606.22537v1 Announce Type: new Abstract: Out-of-Distribution (OOD) detection is essential for ensuring the robustness and reliability of object detection systems deployed in safety-critical app
arXiv:2606.23668v1 Announce Type: new Abstract: Large Language Models (LLMs) are frequently portrayed as general-purpose solvers capable of solving arbitrary tasks. We argue that this view overlooks a
arXiv:2606.20764v1 Announce Type: new Abstract: Reliable spatial decision automation, such as autonomous driving and maritime surveillance, critically depends on robust visual perception. However, rea
arXiv:2606.23676v1 Announce Type: new Abstract: AdamW is the de facto optimizer for training large language models (LLMs), yet the theory behind it still lives mostly in finite-variance regimes. This
arXiv:2606.23256v1 Announce Type: new Abstract: The increasing maturity of embodied AI platforms has driven a growing interest in procedural video representation learning to support intelligent assist
arXiv:2606.20621v1 Announce Type: cross Abstract: Multi-agent debate improves the reliability of large language models (LLMs) through iterative peer critiques. However, fixed topologies often introduc
arXiv:2606.20477v2 Announce Type: replace Abstract: We study how to train visually grounded vision-language models (VLMs) for radiology without manual spatial annotations. We introduce RefRad2D, a lar
arXiv:2606.19120v2 Announce Type: replace-cross Abstract: On-policy self-distillation (OPSD) trains a model on its own rollouts and uses a frozen copy to provide dense token-level targets conditioned
arXiv:2606.20643v1 Announce Type: cross Abstract: Electrical circuit diagram QA tasks require complex mathematical reasoning, which remains challenging for multimodal LLMs. We present SPARC, a multi-a
arXiv:2606.23568v1 Announce Type: new Abstract: Large language models (LLMs) achieve remarkable performance across a wide range of tasks, but their deployment is constrained by substantial memory and
arXiv:2603.21478v2 Announce Type: replace-cross Abstract: Speech technologies have advanced rapidly and serve diverse populations worldwide. However, many languages remain underrepresented due to limi
arXiv:2606.21661v1 Announce Type: new Abstract: Generating a coherent multi-shot video requires structured cross-shot memory. Subject appearance, scene context, and speaker identity must persist acros