Knowledge catalogue
Opportunistic Expert Activation (OEA) is a batch-aware expert routing technique for mixture-of-experts models that enables faster decoding without requiring model retraining. The method optimizes whic
arXiv:2606.31639v1 Announce Type: cross Abstract: Large language models are no longer only text generators. They are increasingly embedded in retrieval pipelines, enterprise assistants, coding environ
arXiv:2509.15443v2 Announce Type: replace-cross Abstract: Human-to-humanoid imitation learning presents a promising pathway to address the severe data scarcity bottleneck in robotics by utilizing abun
arXiv:2606.31084v1 Announce Type: cross Abstract: Merge with Motion Vector Difference (MMVD) is a key coding tool in Versatile Video Coding for improving motion prediction accuracy. However, its exhau
arXiv:2606.31054v1 Announce Type: cross Abstract: Multimodal Large Language Models (MLLMs) are critically hampered by hallucination, generating content inconsistent with the provided image. In this pa
The search results show llama.cpp releases but do not contain specific information about release b9853. Based on the context from the llama.cpp project, b9853 is likely a development build release of
Release b9859 of llama.cpp was released on July 1, 2026 , and includes updates to allow loading precompiled binary kernels from library in the OpenCL backend . This release continues development of th
arXiv:2606.22723v2 Announce Type: replace Abstract: Although Large Language Models (LLMs) excel in many tasks, their assessment in Portuguese has received less attention, particularly for open-ended,
arXiv:2606.31420v1 Announce Type: new Abstract: Test-Time Adaptation (TTA) enables models trained on a source domain to adapt online to unlabeled test data under distribution shifts. While recent TTA
arXiv:2606.31844v1 Announce Type: cross Abstract: A local-to-global context mismatch arises when autoregressive traffic simulators trained on ego-centric driving logs are deployed in globally observab
Vercel has restored access to Claude Fable 5 on its AI Gateway service, allowing developers to integrate the model into their applications through Vercel's platform. This restoration enables continued
arXiv:2606.31909v1 Announce Type: new Abstract: In this work, we study Compositional Dexterous Functional Object Manipulation (CD-FOM): tasks such as aiming and actuating a spray bottle on a plant or
arXiv:2410.00074v2 Announce Type: replace Abstract: A novel Learning-by-Education Node Community framework (LENC) for Collaborative Knowledge Distillation (CKD) is presented, which facilitates continu
arXiv:2606.30676v1 Announce Type: cross Abstract: Deploying spiking neural networks (SNNs) on neuromorphic hardware demands aggressive synaptic pruning while preserving temporal computation integrity.
arXiv:2606.31718v1 Announce Type: cross Abstract: Relation extraction (RE) for low-resource languages is typically constrained by the lack of annotated corpora. We investigate the feasibility of cross
arXiv:2606.32020v1 Announce Type: new Abstract: Modern one-step diffusion models achieve impressive quality through distribution-based timestep distillation. Yet, they rely on a critical assumption: T
arXiv:2606.31085v1 Announce Type: new Abstract: Drug-drug interaction (DDI) prediction is essential for medication safety, yet it requires reasoning over heterogeneous biomedical evidence whose releva
arXiv:2606.31232v1 Announce Type: new Abstract: Learning visual world models for planning requires compact latent dynamics that remain sensitive to actions, yet reconstruction-free joint-embedding obj
arXiv:2606.30780v1 Announce Type: cross Abstract: Audio deepfakes are a growing challenge for the general public, as well as for journalists and fact-checkers. The latter need reliable tools to verify
arXiv:2606.31197v1 Announce Type: new Abstract: Accurate 4D trajectory prediction and closed-loop tracking are essential for Unmanned Aerial Vehicle (UAV) swarms to achieve safe and efficient operatio
arXiv:2606.31198v1 Announce Type: cross Abstract: Real-time video segmentation of the prostate in Transrectal Ultrasound (TRUS) is essential for image-guided interventions. While conventional 2D metho
arXiv:2606.31095v1 Announce Type: new Abstract: Reconstructing anatomically faithful vascular structures from clinically accessible imaging modalities is of substantial clinical significance. However,
arXiv:2606.32028v1 Announce Type: new Abstract: Video-based embodied world models provide an appealing substrate for robotic manipulation by predicting future states, yet current approaches remain lim
arXiv:2606.30664v1 Announce Type: cross Abstract: The coupon incentive is one of the most common tools marketers use to court users to engage with a business at various stages of the customer life cyc
arXiv:2606.30665v1 Announce Type: cross Abstract: Stage B heart failure is characterized by asymptomatic structural or functional cardiac abnormalities. Identifying individuals at this stage is clinic
arXiv:2606.31742v1 Announce Type: cross Abstract: Explainable AI (XAI) methods have demonstrated significant success in recent years at identifying relevant features in input data that drive deep lear
arXiv:2412.02798v3 Announce Type: replace Abstract: We consider the problem of reconstructing a HxWx31 hyperspectral image from a Himes W grayscale snapshot measurement that is captured using only a s
arXiv:2606.31938v1 Announce Type: cross Abstract: Deploying Vision Transformer (ViT) models on edge platforms remains challenging due to their high computational demands and the architectural heteroge
arXiv:2512.04390v2 Announce Type: replace-cross Abstract: Joint video super-resolution and deblurring (VSRDB) requires both efficient long-range temporal modeling and robustness to frame-wise exposure
arXiv:2606.30704v1 Announce Type: cross Abstract: Large language models (LLMs) excel across a wide range of tasks, yet their instance-specific solutions often lack the structural consistency needed fo
arXiv:2601.21291v2 Announce Type: replace Abstract: Depth completion aims to predict a dense depth map from a color image with sparse depth measurements. Although deep learning methods have achieved s
arXiv:2606.30901v1 Announce Type: new Abstract: Prototype-based medical image classifiers present three clinical limitations: they treat findings as independent, silently amplify unsafe physician feed
arXiv:2603.26266v3 Announce Type: replace Abstract: Large vision-language models have endowed GUI agents with strong general capabilities for interface understanding and interaction. However, due to i
arXiv:2606.31096v1 Announce Type: new Abstract: Long-range 3D object detection is critical for safe autonomous driving at highway speeds, yet existing radar-camera fusion methods remain limited at ext
arXiv:2602.06323v2 Announce Type: replace Abstract: Epidemiological forecasting from surveillance data is a hard problem and hybridizing mechanistic compartmental models with neural models is a natura
Hugging Face and Cerebras have collaborated to integrate Google's Gemma 4 model with real-time voice AI capabilities, enabling faster speech processing and voice interactions. This integration likely
arXiv:2601.08187v3 Announce Type: replace Abstract: Large language models (LLMs) have demonstrated promising capabilities in Text-Attributed Graph (TAG) understanding. Recent studies typically focus o
arXiv:2606.31695v1 Announce Type: new Abstract: The performance of deep spiking neural networks (SNNs) often relies on batch normalization (BN). However, the advanced dynamic BN variants used in state
arXiv:2606.15837v2 Announce Type: replace Abstract: Deep neural networks (DNNs) frequently fail to generalize to out-of-distribution (OOD) medical images because of variations in scanners and acquisit
arXiv:2410.12341v4 Announce Type: replace-cross Abstract: As AI-generated content increasingly populates the web, generative AI models are at growing risk of being trained on their own outputs, a proc
arXiv:2601.22123v4 Announce Type: replace Abstract: Simulating the long-time evolution of Hamiltonian systems is limited by the small timesteps required for stable numerical integration. To overcome t
arXiv:2606.30951v1 Announce Type: cross Abstract: Micro-ultrasound (muUS) is a new, emerging, and promising imaging modality for prostate cancer (PCa) detection, but accurate identification of suspici
arXiv:2603.14579v3 Announce Type: replace Abstract: Vision language models (VLMs) have shown significant promise in visual grounding for images as well as videos. In medical imaging research, VLMs rep
arXiv:2606.31734v1 Announce Type: new Abstract: Video World Models are interactive video generation models that predict future world states based on user actions and history video frames. A critical c
arXiv:2606.31167v1 Announce Type: cross Abstract: VLA models have emerged as a powerful paradigm for transferring semantic knowledge from web-scale data to physical robotic control. However, current s
arXiv:2606.31717v1 Announce Type: new Abstract: Low-rank adaptation (LoRA) is commonly viewed as an update-space approximation to full fine-tuning, yet this view is incomplete for self-gated Transform
arXiv:2606.31026v1 Announce Type: cross Abstract: We propose OTCache, a training-free framework for accelerating diffusion sampling via caching schedule prediction. Existing graph-based caching method
arXiv:2606.30936v1 Announce Type: cross Abstract: Generative Astrodynamics is advanced in this work by extending generative modelling to an orbit determination problem in the cislunar environment. The
arXiv:2606.32036v1 Announce Type: new Abstract: Producing 3D human representations from input views on the fly is essential for immersive live streaming systems, where representation compactness is as
arXiv:2606.30673v1 Announce Type: cross Abstract: Autoregressive Transformers dominate high-quality mesh generation by producing artist-worthy topologies, yet their inherent sequential decoding induce
arXiv:2606.31626v1 Announce Type: new Abstract: Existing smartphone image quality assessment (IQA) methods commonly reduce perceptual quality to a single score. However, this scalar formulation is poo
This post from Ollama's official X account discusses performance improvements for the Gemma 4 model, likely covering optimizations related to MLX (Machine Learning eXperimental framework) and MTP (Mul
ParallelKernelBench is a benchmark tool or methodology developed by Together AI for evaluating the performance of parallel kernel execution in machine learning systems. The benchmark likely measures m
arXiv:2606.31834v1 Announce Type: cross Abstract: Real-world detectors for autonomous driving, surveillance, and robotics must handle domain-shifts under strict latency and memory constraints, yet exi
arXiv:2606.31160v1 Announce Type: new Abstract: Modern Vision-Language-Action (VLA) planners for autonomous driving emit a chain-of-causation (CoC) reasoning step before producing a trajectory. The re
arXiv:2606.31895v1 Announce Type: new Abstract: LiDAR has increasingly been integrated into traffic cameras to expand coverage and mitigate occlusion in roadside cooperative perception. However, how u
We're excited to introduce US-based frontier open-weight models in AWS GovCloud (US). With this release, Amazon Bedrock now supports OpenAI’s open-weight GPT OSS models (120B and 20B) and NVIDIA Nemot
arXiv:2606.31285v1 Announce Type: new Abstract: Human reasoning is inherently multimodal: when problems become difficult, we rarely think in words alone. We often externalize our reasoning by sketchin
arXiv:2509.17246v2 Announce Type: replace Abstract: We introduce SPFSplatV2, an efficient feed-forward framework for 3D Gaussian splatting from sparse multi-view images, requiring no ground-truth pose
arXiv:2606.31781v1 Announce Type: cross Abstract: Log parsing is a fundamental step in automated log analysis, transforming raw system logs into structured event templates for downstream tasks such as