Knowledge catalogue
arXiv:2604.28056v1 Announce Type: new Abstract: Large language models (LLMs) make reward design in reinforcement learning substantially more scalable, but generated rewards are not automatically relia
arXiv:2604.27358v1 Announce Type: new Abstract: As large language model (LLM) agents are deployed in high-stakes environments, the question of how safely to delegate subtasks to specialized sub-agents
arXiv:2604.28032v1 Announce Type: new Abstract: We study d-dimensional unbiased mean estimation in the single-message shuffle model, where each user sends a single privatized message and the analyzer
arXiv:2604.27964v1 Announce Type: new Abstract: Assumption-Based Argumentation (ABA) is a well-established formalism for modelling and reasoning over debates, with a wide range of applications. Howeve
arXiv:2604.27329v1 Announce Type: cross Abstract: 3D shapes from scanning, reconstruction, or AI-generated content often lack simple quad mesh layouts -- critical for efficient editing and modeling. E
The AI industry is racing toward superintelligence. Dan and Scaled Cognition built something more : Super-Reliable Intelligence. 'The smartest model in the world is useless if it can’t get the answer
arXiv:2604.27398v1 Announce Type: new Abstract: For constructing text embeddings, mean pooling, which averages token embeddings, is the standard approach. This paper examines whether mean pooling actu
AI21 Labs achieved state-of-the-art performance on the BrowseComp-Plus benchmark with 95.18% accuracy using their AI21 Maestro model with agent optimization techniques. The post appears to discuss aut
4/5 But then we’re left with a search space problem. The possible agent configurations are infinite. And even if you manually optimize, what happens when a better model drops? Or your use case data up
arXiv:2604.25942v1 Announce Type: new Abstract: Left ventricular ejection fraction (LVEF) assessment depends on echocardiography, limiting access in primary care and resource-constrained settings. We
arXiv:2604.26379v1 Announce Type: new Abstract: Reliable seizure detection in mouse models is essential for preclinical epilepsy research, yet manual review of synchronized video-EEG recordings is lab
arXiv:2601.11568v2 Announce Type: replace-cross Abstract: Training Large Language Models (LLMs) is highly memory-intensive due to optimizer state overhead. The FRUGAL framework mitigates this with gra
arXiv:2604.25965v1 Announce Type: cross Abstract: Deep learning models are widely deployed in safety-critical domains, but remain vulnerable to adversarial attacks. In this paper, we study the adversa
arXiv:2604.26437v1 Announce Type: new Abstract: Purpose: Rapid and reliable diagnostic tools are crucial for managing respiratory diseases like COVID-19, where chest X-ray analysis coupled with artifi
arXiv:2604.26809v1 Announce Type: new Abstract: Federated Unlearning (FU) is an emerging paradigm in Federated Learning (FL) that enables participating clients to fully remove their contributions from
B8984 is a build/release version of llama.cpp, an open-source C/C++ library for large language model inference. Llama.cpp enables LLM inference with minimal setup and state-of-the-art performance on a
Release b8987 of llama.cpp updates cpp-httplib to version 0.43.2 . This is a minor maintenance release from the llama.cpp project, which provides C/C++ inference for large language models. The release
llama.cpp b8990 is a release version of a C/C++ LLM inference tool from the ggml-org project. The release likely contains bug fixes, performance improvements, or new features for local language model
arXiv:2604.26310v1 Announce Type: new Abstract: Fine-grained emotion classification, which identifies specific emotional states such as happiness, anger, sadness, and fear, remains a challenging task
NVIDIA DLSS 4.5 introduces Dynamic Multi Frame Generation and a second-generation transformer model, improving game image quality and frame rates while maintaining responsiveness. A new TensorRT for R
arXiv:2604.26176v1 Announce Type: cross Abstract: The integration of Large Language Models (LLMs) with Retrieval-Augmented Generation (RAG) has significantly advanced Knowledge Graph Question Answerin
arXiv:2604.26172v1 Announce Type: cross Abstract: We develop a physics-informed learning framework for energy-shaping control of port-Hamiltonian (pH) systems from trajectory data. The proposed approa
arXiv:2505.13518v2 Announce Type: replace-cross Abstract: Imbalanced datasets, where one class significantly outnumbers others, remain a persistent challenge in machine learning, often biasing predict
Distillation is largely an industry standard and not just something done by Chinese labs targeting OpenAI/Anthropic. Many American companies also distill Chinese (open) models. LIVE TRIAL UPDATE: Open
arXiv:2604.26557v1 Announce Type: cross Abstract: The increasing deployment of Large Language Model (LLM) inference on edge AI systems demands efficient execution under tight memory budgets. A key cha
arXiv:2506.07179v2 Announce Type: replace-cross Abstract: Traffic prediction is a critical task in spatial-temporal forecasting with broad applications in travel planning and urban management. To mode
arXiv:2604.25923v1 Announce Type: new Abstract: Recent advances in large language models (LLMs) have prompted a growing body of work that questions the methodology of prevailing evaluation practices.
arXiv:2603.19199v2 Announce Type: replace-cross Abstract: Real-time execution is crucial for deploying Vision-Language-Action (VLA) models in the physical world. Existing asynchronous inference method
arXiv:2604.26084v1 Announce Type: cross Abstract: Accurate fruit maturity identification is essential for determining harvest timing, as incorrect assessment directly affects yield and post-harvest qu
arXiv:2604.26197v1 Announce Type: cross Abstract: Large Language Model (LLM) agents are increasingly used in real-world products, where personalized and context-aware user interactions are essential.
arXiv:2509.21983v2 Announce Type: replace-cross Abstract: Constructing robots to accomplish long-horizon tasks is a long-standing challenge within artificial intelligence. Approaches using generative
arXiv:2502.11614v3 Announce Type: replace-cross Abstract: Prior studies have shown that distinguishing text generated by Large Language Models (LLMs) from human-written one is highly challenging for h
arXiv:2604.26454v1 Announce Type: new Abstract: Monocular depth estimation (MDE) is a fundamental yet inherently ill-posed task. Recent vision foundation models (VFMs), particularly DINO-based transfo
arXiv:2604.25929v1 Announce Type: new Abstract: Large Language Models (LLMs) are increasingly used to generate pictures, texts, music, videos, and other works that have traditionally required human cr
arXiv:2604.26591v1 Announce Type: cross Abstract: Technology mapping is a critical yet challenging stage in logic synthesis. While Large Language Models (LLMs) have been applied to generate optimizati
arXiv:2604.26390v1 Announce Type: cross Abstract: Balancing differential privacy (DP) with recommendation accuracy is a key challenge in privacy-preserving recommender systems, since DP-noise degrades
arXiv:2509.25236v3 Announce Type: replace Abstract: A core challenge in causal artificial intelligence is the principled coordination of multiple, imperfect, and subjective causal perspectives arising
arXiv:2604.26136v1 Announce Type: cross Abstract: Preserving a speaker's voice identity while generating speech in a different language remains a fundamental challenge in spoken language technology, p
arXiv:2603.05959v3 Announce Type: replace Abstract: Reconstructing 3D geometry from streaming video requires continuous inference under bounded resources. Recent geometric foundation models achieve im
arXiv:2507.19067v2 Announce Type: replace-cross Abstract: Recommender systems based on graph neural networks (GNNs) have been proved to perform well on user-item interactions. However, they commonly s
Pi + @huggingface llamacpp + Qwen3.6 = 🔥🔥🔥🔥 turns out not killing the prefix cache all the time and notnhaving a humongous set of tools and a massive system prompt is good for local model use. who'd h
arXiv:2603.15262v2 Announce Type: replace Abstract: Modern e-commerce search is evolving to resolve complex user intents. While Large Language Models (LLMs) offer strong reasoning, existing LLM-based
arXiv:2604.17612v2 Announce Type: replace-cross Abstract: Multi-agent systems built on large language models (LLMs) are difficult to reason about. Coordination errors such as deadlocks or type-mismatc
arXiv:2604.26505v1 Announce Type: cross Abstract: Dynamic quantization emerged as a practical approach to increase the utilization and efficiency of the machine learning serving flow. Unlike static qu
The recent KubeCon + CloudNativeCon Europe event did not read like a celebration so much as an admission. AI is everywhere, but the systems underneath it are strained — not by models, but by layout. T
arXiv:2603.10225v3 Announce Type: replace-cross Abstract: Cross-entropy loss has long been the standard choice for training deep neural networks, yet it suffers from interpretability limitations, unbo
arXiv:2604.26496v1 Announce Type: new Abstract: Adversarial Training (AT) is one of the most effective methods for developing robust deep neural networks (DNNs). However, AT faces a trade-off problem
arXiv:2508.12672v4 Announce Type: replace-cross Abstract: Federated Learning (FL) enables collaborative model training across multiple clients without sharing private data. We consider FL scenarios wh
arXiv:2604.26394v1 Announce Type: cross Abstract: Recent advances in large language models and agentic frameworks have enabled virtual customer assistants (VCAs) for complex support. We present SecMat
arXiv:2604.26940v1 Announce Type: new Abstract: Small language models (SLMs) offer computational efficiency for scalable deployment, yet they often fall short of the reasoning power exhibited by their
arXiv:2511.13285v2 Announce Type: replace Abstract: Artistic design, particularly poster design, often demands rapid yet precise modification of textual content while preserving visual harmony and typ
The TensorRT for RTX plugin provides a runtime for Unreal Engine's Neural Network Engine (NNE), enabling efficient deployment of AI models directly within real-time applications. Developers can see 1.
arXiv:2604.26422v1 Announce Type: cross Abstract: Accurate end-to-end tail-latency forecasting is critical for proactive SLO management in microservice systems. However, modeling long-range dependency
Jerry Liu discusses a key limitation of state-of-the-art large language models at AI Dev Day '26, highlighting that while modern LLMs excel at building applications, they struggle with fundamental tas
Nous Research is acknowledging and thanking Rugved Somwanshi and the LM Studio team for their contribution via a pull request (PR) to a project, likely related to Nous Research's open-source model dev
The migration in numbers: - Team of 16 engineers worked over 6 weeks. - We reduced our footprint from 6M CPU cores, to just 10k cores. - We are now using the same Grok-based transformer models that po
It's been almost three years since Silicon Valley started aggressively pushing large language model-based chatbots like ChatGPT as the supposedly inevitable future of everything, and there's no group
I cannot verify the authenticity of this post or its specific claims about Grok 4.3's performance metrics. The source appears to reference xAI's Grok model improving significantly on benchmark leaderb
arXiv:2509.09870v2 Announce Type: replace-cross Abstract: Large language models (LLMs) enable conversational agents (CAs) to express distinctive personalities, raising new questions about how such des
arXiv:2604.26218v1 Announce Type: new Abstract: Brain encoding models not only serve to decipher how visual stimuli are transformed into neural responses, but also represent a critical step toward vis