Knowledge catalogue
arXiv:2605.19485v1 Announce Type: new Abstract: Large Reasoning Models (LRMs) have demonstrated remarkable capabilities in solving complex problems by generating structured, step-by-step reasoning con
arXiv:2605.19847v1 Announce Type: cross Abstract: Multi-tenant retrieval-augmented generation (RAG) services advertise per-account differential privacy as the operative leakage boundary: each account'
arXiv:2605.18891v1 Announce Type: cross Abstract: Evaluations of unlearning on reasoning models sometimes show a bypass pattern. The answer side looks unlearned, but the model's own thinking trace kee
Australian teenagers who were unable to access social media due to age verification requirements implemented under new legislation showed reduced news consumption compared to their peers. The finding
arXiv:2605.18833v1 Announce Type: cross Abstract: Automated data quality assessment is crucial for managing big data, but existing solutions face challenges in achieving accurate context-aware assessm
arXiv:2605.19043v1 Announce Type: cross Abstract: Automated grading systems have enabled scalable assessment for many response types, but handwritten mathematics remains a barrier due to the complexit
arXiv:2605.19136v1 Announce Type: new Abstract: Simulation is a central tool for scalable robot learning, but its effectiveness depends on the quality of object assets. While modern 3D datasets provid
Enterprises have figured out how to stand up AI agents, but agent management is another problem entirely. The agentic moment is forcing organizations to interrogate everything, including the operating
arXiv:2605.20025v1 Announce Type: new Abstract: Automating scientific discovery requires more than generating papers from ideas. Real research is iterative: hypotheses are challenged from multiple per
arXiv:2605.19698v1 Announce Type: cross Abstract: Text-to-image diffusion models are increasingly developed through open-source reuse and repeated downstream fine-tuning, where reused checkpoints are
arXiv:2605.19778v1 Announce Type: new Abstract: We introduce B-cos GNNs, an inherently explainable class of graph neural networks whose predictions decompose exactly into per-node, per-feature contrib
Build b9239 is a llama.cpp release that includes a fix for the --fit verbosity flag when used with --verbosity 4 . The release provides compiled binaries for multiple platforms including macOS (Apple
b9240 is a release of llama.cpp that includes a fix for the --help option related to the --verbosity flag . The release provides prebuilt binaries across multiple platforms including macOS (Apple Sili
b9244 is an intermediate build release of llama.cpp, a C/C++ implementation framework for running large language models with GGUF format support. The release includes pre-compiled binaries for multipl
llama.cpp release b9245, published on May 20, 2026, includes a CUDA optimization for RDNA3 Q6_K MMVQ performance tuning. The release provides pre-built binaries for multiple platforms including macOS,
B9251 is a build identifier for a release in the llama.cpp project, which enables LLM inference with minimal setup and state-of-the-art performance on a wide range of hardware - locally and in the clo
b9253 is the latest version of llama.cpp, released on May 20, 2026. Llama.cpp is a project for LLM inference in C/C++. This build includes bug fixes, performance improvements, and features for running
arXiv:2602.09872v2 Announce Type: replace Abstract: Human activity recognition (HAR) on resource constrained devices requires high accuracy across diverse sensor setups. Selective state space models (
arXiv:2605.19262v1 Announce Type: new Abstract: Masked diffusion language models (MDLMs) are emerging as a compelling new paradigm for text generation, but their training-time security remains largely
arXiv:2605.19433v1 Announce Type: cross Abstract: Large language models (LLMs) have achieved remarkable success in complex reasoning tasks via long chain-of-thought (CoT), yet their immense computatio
arXiv:2605.20084v1 Announce Type: cross Abstract: Large language models (LLMs) can enhance factuality via retrieval-augmented generation (RAG), but applying RAG to every query is unnecessary when the
Banger take Gavin Baker: 'I've been optimistic that the fundamental shortage of wafers, which is really controlled by Taiwan Semi, will prevent a bubble.' 'If Taiwan Semi did what Jensen wanted, Nvidi
arXiv:2605.19516v1 Announce Type: cross Abstract: As AI-generated text enters the real-world at scale, institutions increasingly use commercial AI-text detectors, especially in education and academic-
arXiv:2506.17036v2 Announce Type: replace-cross Abstract: Modern industrial systems are often subject to multiple failure modes, and their conditions are monitored by multiple sensors, generating mult
arXiv:2605.18927v1 Announce Type: cross Abstract: Bayesian latent space models offer a principled approach to network representation, but rely on correct specification of both geometry and link functi
arXiv:2603.14918v2 Announce Type: replace-cross Abstract: Model-based approaches for (bio)process systems often suffer from incomplete knowledge of the underlying physical, chemical, or biological law
arXiv:2605.19646v1 Announce Type: cross Abstract: Advancements in clinical Brain-Computer Interfaces (BCIs) depend on precise and reliable signal interpretation. However, the high-dimensional and nois
arXiv:2605.19147v1 Announce Type: cross Abstract: Large language models (LLMs) are highly susceptible to backdoor attacks (BAs), wherein training samples are poisoned using trigger-based harmful conte
This post discusses a reactive programming or state management architecture where individual behaviors function as small, independent units that respond to state changes and generate new state changes
Behind the scenes with Sundar Pichai and Demis Hassabis, two of the most important people in AI We covered timelines to curing every disease, AGI bottlenecks, democratizing AI healthcare, and the futu
LLMs have become more powerful at smaller sizes, but deploying them to edge devices like smartphones remains a massive challenge. Today, developers have to optimize across a sprawling combination of a
arXiv:2605.19639v1 Announce Type: new Abstract: Text-to-Image (T2I) models and Unified Multimodal Models (UMMs) have achieved remarkable progress in visual generation. However, their reliance on a sin
arXiv:2605.19069v1 Announce Type: cross Abstract: Code-switching -- the natural alternation between two languages within a single utterance -- represents one of the most challenging and under-studied
arXiv:2512.05721v2 Announce Type: replace Abstract: Traditional cellular traffic forecasting models are optimized for minimizing symmetric errors, leaving them indifferent to shifting operational prio
arXiv:2605.19919v1 Announce Type: new Abstract: Pretrained imitation policies have become a strong foundation for robot manipulation, but they often require online improvement to overcome execution er
arXiv:2605.19986v1 Announce Type: cross Abstract: Fine-grained manipulation marks a regime where global scene context no longer suffices, and success hinges on the tight coupling of local attribute gr
arXiv:2605.19249v1 Announce Type: new Abstract: Time-series forecasting is critical in various scenarios, such as energy, transportation, and public health. However, most existing forecasters rely pri
arXiv:2605.19771v1 Announce Type: cross Abstract: Existing imitation learning methods for end-to-end autonomous driving predominantly learn from successful demonstrations by minimizing geometric devia
arXiv:2605.20107v1 Announce Type: cross Abstract: JEPAs often regularize one-view embeddings toward an isotropic Gaussian, implicitly baking Euclidean symmetry into the representation. We show that th
arXiv:2510.25348v2 Announce Type: replace Abstract: Information cascade popularity prediction is a key problem in analyzing content diffusion in social networks. However, current related works suffer
arXiv:2510.01499v2 Announce Type: replace-cross Abstract: With the rapid progress of multi-agent large language model (LLM) reasoning, how to effectively aggregate answers from multiple LLMs has emerg
arXiv:2605.19461v1 Announce Type: new Abstract: On-policy reinforcement learning methods like GRPO suffer from mode collapse: they exhibit reduced solution diversity, concentrating probability mass on
arXiv:2605.20127v1 Announce Type: cross Abstract: Artificial vision models are often evaluated against the human visual cortex by measuring how accurately their internal representations predict brain
arXiv:2605.19674v1 Announce Type: new Abstract: Strategic classification(SC) studies the interaction between decision models and agents who strategically manipulate their features for favorable outcom
arXiv:2605.19420v1 Announce Type: new Abstract: Grounding open-ended semantic instructions into physically executable local goals is a fundamental challenge in human-robot interaction. While existing
arXiv:2605.19620v1 Announce Type: new Abstract: LiDAR-based 3D human motion capture has broad applications in fields such as autonomous driving and robotics, where accurate motion reconstruction is cr
arXiv:2605.19255v1 Announce Type: new Abstract: Existing bilateral teleoperation platforms still rely on costly rigid six-axis force/torque sensors, tightly coupled leader-follower hardware, and kiloh
arXiv:2605.19518v1 Announce Type: new Abstract: Generating Knowledge Graphs (KGs) remains one of the most time-consuming and labor-intensive tasks for knowledge engineers, as they need to identify sem
arXiv:2605.18807v1 Announce Type: cross Abstract: Encoder-decoder models offer substantial inference-time savings over decoder-only models, but their pretraining objectives suffer from sparse supervis
arXiv:2605.19972v1 Announce Type: cross Abstract: Vector quantization is a fundamental primitive for scalable machine learning systems, enabling memory-efficient storage, fast retrieval, and compresse
arXiv:2605.19532v1 Announce Type: new Abstract: Text-to-image diffusion models can synthesize high-quality images, yet the outcome is notoriously sensitive to the random seed: different initial seeds
Both LlamaParse and LiteParse can be used with your favorite agent through minimal MCP/skill setup: ✅ Setup LlamaParse MCP for high-quality document processing and extraction: https://www.llamaindex.a
arXiv:2605.19352v1 Announce Type: cross Abstract: Understanding how humans and artificial intelligence systems predict and plan by interacting with their environment is a fundamental challenge at the
brain dump of how/why we use Evals to measure agents before & after shipping to prod 1. Good Evals simulate what our real users will do and encounter. They’re not really random benchmark tasks, they r
arXiv:2605.19324v1 Announce Type: new Abstract: Efficient neural network models that generate brain-like dynamic activity can be a valuable resource for generating synthetic data, analyzing difference
Elon Musk posted a congratulatory message directed at Jeff Bezos on X (formerly Twitter), likely referencing a recent achievement or announcement by the Amazon founder. Without access to the specific
⚠️👇 🚨Breaking ⚠️ If we can’t make AI agents follow rules, we are screwed. New study from METR reports that “when the agents were faced with hard tasks, they routinely violated constraints” This—routin
arXiv:2605.19929v1 Announce Type: cross Abstract: Low-bit post-training quantization (PTQ) is a pivotal technique for deploying Vision-Language Models (VLMs) on resource-constrained devices. However,
arXiv:2605.19172v1 Announce Type: cross Abstract: Forecasting urban delivery demand becomes substantially more challenging when newly added service regions lack historical records. Existing spatiotemp
btw we did a bake off of Exa vs competitors and it took all of 1.5 hrs for the team to unanimously converge on exa lol. so proud to see my former landlords crush it - time travel back to last year and