Knowledge catalogue
arXiv:2608.05724v1 Announce Type: new Abstract: Sparse word embedding pipelines can avoid dense co-occurrence matrix materialization, dense factorization, and gradient training while still relying on
arXiv:2608.03228v1 Announce Type: new Abstract: Existing low rank KV cache methods preserve either model weights or key variance, neither of which directly reflects the attention scores used during in
arXiv:2608.03887v1 Announce Type: new Abstract: Fine-tuning a large language model on new data degrades what it previously learned. We present Omega-S, a drop-in penalty computed from the weight matri
arXiv:2607.24819v1 Announce Type: cross Abstract: Wafer fabrication exhibits unique characteristics, including reentrant process flows, variable bottlenecks, and highly variable process conditions. In
arXiv:2607.20265v1 Announce Type: cross Abstract: Large-scale pretrained language models such as T5 and BERT have demonstrated strong capabilities for generating structured knowledge. However, their p
arXiv:2607.06585v1 Announce Type: new Abstract: Plant diseases, resulting from both biotic and abiotic stresses, cause an estimated 20-40% loss in global agricultural yield annually, resulting in econ
arXiv:2606.31575v1 Announce Type: new Abstract: Reinforcement learning (RL) has become a powerful tool for propelling Large Language Models (LLMs) beyond imitation-based training towards more robust r
arXiv:2606.24421v1 Announce Type: new Abstract: Spectral filtering recently delivered substantial pruning for static subgraph matching: Laplacian interlacing rejects candidates whose neighborhoods can
arXiv:2606.13189v2 Announce Type: replace Abstract: Prompt-based LLMs are increasingly used for stance detection, but harder examples are not always repaired by clearer instructions, reasoning prompts
arXiv:2606.19813v1 Announce Type: cross Abstract: Thermal infrared (TIR) imaging has been a popular choice for field robotics due to its robust perception capability under low light visual degradation
arXiv:2602.02431v2 Announce Type: replace-cross Abstract: It is folklore that reusing training data more than once can improve the statistical efficiency of gradient-based learning. While this phenome
arXiv:2606.09441v1 Announce Type: new Abstract: Retrieval-Augmented Generation (RAG) injects LLM queries with relevant documents to improve response quality. This injection increases prompt length and
arXiv:2606.07897v1 Announce Type: new Abstract: Current AI models frequently exhibit epistemic sycophancy, endorsing claims to agree with a user. Existing evaluations typically measure this either by
arXiv:2603.24576v2 Announce Type: replace-cross Abstract: Robots often observe information that determines a future action long before that action is executed. In a shell game, for example, a robot fi
arXiv:2606.05489v1 Announce Type: new Abstract: Retrieval systems underpin modern AI applications -- spanning visual search, recommendation engines, and multi-modal question answering. Modern multi-st
arXiv:2506.02075v2 Announce Type: replace-cross Abstract: The current state of evaluation in survival analysis is plagued by the persistent use of evaluation metrics in ways that are misaligned with t
arXiv:2605.29270v1 Announce Type: new Abstract: The era of the Internet of Agents (IoA) is taking shape: LLM agents are expected to fulfill user goals by orchestrating fast-growing populations of Mode
arXiv:2602.02855v2 Announce Type: replace Abstract: Pre-training on a source task is usually expected to facilitate fine-tuning on similar downstream problems. In this work, we mathematically show tha
It is one thing to say AI will change the world. It is another to expect the class of 2026 to applaud it. In fact, when former Google CEO Eric Schmidt told University of Arizona graduates that their t
This is today’s edition of The Download, our weekday newsletter that provides a daily dose of what’s going on in the world of technology. Climate tech companies are going public. What’s next? Solar an
arXiv:2605.24749v1 Announce Type: cross Abstract: Reward modeling is not only a prediction problem: in KL-regularized policy optimization, the learned reward is exponentiated to define the deployed po
arXiv:2605.23986v1 Announce Type: cross Abstract: Memory is a fundamental component for enabling long-context LLM agents, supporting persistent state across interactions through a continuous serve-and
arXiv:2605.25216v1 Announce Type: new Abstract: Recent advances in imitation learning and vision-language models highlight the need for high-fidelity tactile perception, with 6-DoF tactile object pose
arXiv:2603.16077v3 Announce Type: replace Abstract: Masked diffusion models (MDM) exhibit superior generalization when learned using a Partial masking scheme (Prime). This approach converts tokens int
Jerry Liu shared a photo of a sign on 2nd Street visible from a southward-facing direction that advertises or promotes LlamaIndex, suggesting the company has some physical presence or marketing initia
arXiv:2603.01406v2 Announce Type: replace Abstract: Neural PDE solvers are often described as learning solution operators that map problem data to PDE solutions. In this work, we argue that this inter
arXiv:2605.20416v1 Announce Type: new Abstract: We study whether multimodal large language models (MLLMs) can leverage crystallographic plane indices (Miller indices) as a structured latent representa
arXiv:2605.18802v1 Announce Type: cross Abstract: Cardiovascular stability estimation from wearable photoplethysmography (PPG) requires a principled nonlinear framework, yet major gaps persist in heur
arXiv:2605.16481v1 Announce Type: cross Abstract: Long video understanding requires more than large context windows. It also needs a memory mechanism that decides what visual evidence to retain, keeps
arXiv:2605.15082v1 Announce Type: cross Abstract: We study a prototypical situation when a learned predictor can discover useful low-dimensional structure in data, while using fewer samples than are n
arXiv:2605.14550v1 Announce Type: new Abstract: Artificial intelligence in high-stakes tabular domains cannot be evaluated by predictive performance alone, yet current practice still assesses explaina
arXiv:2605.12328v1 Announce Type: new Abstract: Data entry systems remain structurally vulnerable to categorical misclassifications, particularly in small and medium sized enterprises (SMEs). When nom
arXiv:2605.02150v1 Announce Type: cross Abstract: Accurate prediction of physician referral links is essential for optimizing care coordination and reducing fragmentation in healthcare delivery. Howev
arXiv:2605.02489v1 Announce Type: cross Abstract: As the ecosystem of Large Language Model (LLM)-based agents expands rapidly, efficient and accurate Agent Discovery becomes a critical bottleneck for
arXiv:2605.02568v1 Announce Type: new Abstract: DeepSeek-V3.2 and V4 introduce Compressed Sparse Attention (CSA): a lightning indexer (a learned scoring projection over compressed keys) scores them, t
arXiv:2605.00637v1 Announce Type: new Abstract: Dimensionality reduction (DR) techniques are often characterized by whether they preserve global, high-level structures in the data or local, neighborho
arXiv:2604.28142v1 Announce Type: cross Abstract: Multivector retrieval models achieve state-of-the-art effectiveness through fine-grained token-level representations, but their deployment incurs subs
arXiv:2604.26984v1 Announce Type: new Abstract: Representational collapse, where embeddings become anisotropic and lose multi-scale structure, can erode downstream performance long before performance
arXiv:2411.15253v2 Announce Type: replace-cross Abstract: Osteoporosis, a prevalent condition among the aging population worldwide, is characterized by diminished bone mass and altered bone structure,
arXiv:2412.10441v2 Announce Type: replace-cross Abstract: In the burgeoning field of medical imaging, precise computation of 3D volume holds a significant importance for subsequent qualitative analysi
arXiv:2604.23706v1 Announce Type: new Abstract: Histologic assessment of ulcerative colitis (UC) activity is an important endpoint in clinical trials and routine care, but manual grading with indices
arXiv:2604.21645v1 Announce Type: new Abstract: Large-scale Nearest Neighbor (NN) search, though widely utilized in the similarity search field, remains challenged by the computational limitations inh
arXiv:2604.21442v1 Announce Type: new Abstract: The development of 3D scanning technology has enabled the acquisition of massive point cloud models with diverse structures and large scales, thereby pr
arXiv:2604.13077v1 Announce Type: new Abstract: Coronary angiography (CAG) reports contain clinically relevant physiological measurements, yet this information is typically in the form of unstructured
arXiv:2604.13268v1 Announce Type: cross Abstract: Multimodal Large Language Models (MLLMs) have demonstrated strong cross-modal reasoning capabilities, yet their potential for vision-only tasks remain
arXiv:2604.12537v1 Announce Type: cross Abstract: Vision-Language Models (VLMs) have achieved remarkable progress in multimodal understanding, yet their positional encoding mechanisms remain suboptima
With the vLLM Semantic Router team we released Decision 3.0 (d3), our new SOTA decision model family ranging from 0.6B to 27B, Apache-2.0, all reading text, images and video. How it works - Built on Q
It seems Dario's 'too powerful for you users' strategy is paying off: we have two open models at the top of the leaderboard, surpassing every single model from Anthropic. Open source prevails. Even Mi
arXiv:2609.34242v1 Announce Type: cross Abstract: AI agents require memory that preserves information across user-agent exchanges, user-to-user conversations, and group conversations with or without a
Brace yourself: It turns out AI is being optimized for cheating. OpenAI’s agents hacked into Hugging Face to get the answers to a cybersecurity test. Next, they solved a prestigious math problem (or j
From initial testing it seems pretty solid so far. Asked it to compile the latest llama.cpp for CUDA and its doing well so far. If this thing holds up to its score then its SHOCKINGLY good for its siz
arXiv:2607.06013v1 Announce Type: new Abstract: Adaptive gradient methods can favor max-margin separators that differ from gradient descent, yet a fixed positive numerical stability constant eventuall
LlamaIndex is inviting users to process large-scale document collections through its cloud platform at cloud.llamaindex.ai. The post, from LlamaIndex founder Jerry Liu, highlights the platform's capab
arXiv:2606.28573v1 Announce Type: new Abstract: Modern machine learning models are trained by optimizing high-dimensional non-convex empirical risk functions. Such cost functions can have a multitude
arXiv:2606.05104v1 Announce Type: new Abstract: Knowledge benchmarks for LLMs face three issues: scaling-driven designs that do not operationalize disciplinary representativeness; flat-payment annotat
In this post, we look at how to use SOCI on publicly available Deep Learning AMIs and Containers, when to use the various SOCI modes provided by the tool, and how to quickly and efficiently use this t
LlamaIndex held an offsite event in 2026, as announced by Jerry Liu, the project's founder, on social media. The post likely covered updates on the project's direction, team initiatives, or announceme
Sapu is an early-stage biopharmaceutical company developing treatments for hard-to-treat cancers. From its San Diego facility, the team is pioneering a nanomedicine pipeline that takes existing FDA-ap
A research paper (arXiv:2601.11557) proposes replacing the dominant 'HNSW + float32 + cosine similarity' vector database stack with an information-theoretic alternative that uses Maximally Informat...
arXiv:2604.07034v1 Announce Type: cross Abstract: We present KITE, a training-free, keyframe-anchored, layout-grounded front-end that converts long robot-execution videos into compact, interpretable t