Search: “inference”

arXiv:2502.12187v3 Announce Type: replace Abstract: Hallucinations, a phenomenon where a language model (LM) generates nonfactual content, pose a significant challenge to the practical deployment of L

arXiv:2508.01014v4 Announce Type: replace-cross Abstract: Advances in 3D reconstruction and novel view synthesis have enabled efficient and photorealistic rendering. However, images for reconstruction

arXiv:2605.15753v1 Announce Type: cross Abstract: Functional 3D scene graphs offer a versatile and flexible representation for 3D scene understanding and robotic manipulation, defined by object nodes,

arXiv:2605.15336v1 Announce Type: cross Abstract: In this report, we present HoloMotion-1, a humanoid motion foundation model for zero-shot whole-body motion tracking. A key innovation of HoloMotion-1

arXiv:2605.15384v1 Announce Type: cross Abstract: Memory plays a central role in enabling large language models (LLMs) to operate over sequential tasks by accumulating and reusing experience over time

arXiv:2605.16069v1 Announce Type: new Abstract: Timeseries regression models often struggle to leverage large volumes of labeled multimodal data, particularly when the data are irregularly sampled or

arXiv:2512.19701v2 Announce Type: replace-cross Abstract: Accurate prediction of resource consumption and runtime for cloud workflow jobs is critical for scheduling efficiency, yet remains challenging

arXiv:2605.15975v1 Announce Type: new Abstract: We tackle the challenge of building embodied AI agents that can reliably solve long-horizon planning problems. Imitation learning from demonstrations ha

llama.cpp with MTP support makes local models fast enough to use as daily drivers 🚀 Qwen3.6-27B dense generation (on A10G): From 25 tok/s → 45 tok/s (+78%). Two flags on llama-server: --spec-type draf

arXiv:2605.15660v1 Announce Type: new Abstract: Recent diffusion-based methods for material transfer rely on image fine-tuning or complex architectures with assistive networks, but face challenges inc

arXiv:2605.15423v1 Announce Type: cross Abstract: Modern smart vision sensors need on-device intelligence to process video streams, as cloud computing is often impractical due to bandwidth, latency, a

arXiv:2605.16118v1 Announce Type: new Abstract: The source distribution in conditional flow matching is a design parameter that can be calibrated to data, not a default isotropic prior. We exploit thi

arXiv:2605.16107v1 Announce Type: new Abstract: Machine-generated texts (MGTs) pose risks such as disinformation and phishing, underscoring the need for reliable detection. Metric-based methods, which

arXiv:2602.17050v3 Announce Type: replace Abstract: Embedding tables are critical components of large-scale recommendation systems, facilitating the efficient mapping of high-cardinality categorical f

arXiv:2605.15603v1 Announce Type: cross Abstract: Model-based reinforcement learning (RL) offers a compelling approach to offline RL by enabling value learning on imagined on-policy trajectories. Howe

arXiv:2605.15246v1 Announce Type: new Abstract: Trajectory data is fundamental to modern urban intelligence, yet its sensitivity raises significant privacy concerns. Generative models such as Generati

arXiv:2605.06475v1 Announce Type: cross Abstract: We introduce a probabilistic approach for dating historical manuscript pages from visual features alone. Instead of aggregating centuries into classes

arXiv:2605.16142v1 Announce Type: new Abstract: LLMs have shown impressive success in program synthesis, discovering programs that surpass prior solutions. However, these approaches rely on simple num

arXiv:2403.13805v2 Announce Type: replace-cross Abstract: CLIP (Contrastive Language-Image Pre-training) uses contrastive learning from noise image-text pairs to excel at recognizing a wide array of c

arXiv:2605.16052v1 Announce Type: new Abstract: Recent advances in large language models (LLMs) have significantly enhanced automated legal reasoning. Yet, it remains unclear whether their performance

arXiv:2501.19128v5 Announce Type: replace-cross Abstract: In many real-world scenarios, reward signal for agents are exceedingly sparse, making it challenging to learn an effective reward function for

arXiv:2602.14092v2 Announce Type: replace-cross Abstract: Operating complex real-world systems, such as soft robots, can benefit from precise predictive control schemes that require accurate state and

arXiv:2602.01970v2 Announce Type: replace Abstract: Reinforcement learning enhances the reasoning capabilities of large language models but often involves high computational costs due to rollout-inten

arXiv:2601.12894v2 Announce Type: replace-cross Abstract: Diffusion Policy has dominated action generation due to its strong capabilities for modeling multi-modal action distributions, but its multi-s

arXiv:2509.21465v3 Announce Type: replace Abstract: Tabular foundation models are becoming increasingly popular for low-resource tabular problems. These models make up for small training datasets by p

arXiv:2505.15692v5 Announce Type: replace Abstract: Reinforcement learning (RL) has emerged as an effective paradigm for enhancing model reasoning. However, existing RL methods like GRPO typically rel

arXiv:2605.15656v1 Announce Type: cross Abstract: Under the trend of multi-waveform coexistence in 6G IoT, intelligent receivers must first identify physical-layer waveform types before performing cor

arXiv:2605.15465v1 Announce Type: new Abstract: Physiological time series signals reflect complex, multi-scale dynamical processes of the human body. Existing modeling studies focus on static tasks su

arXiv:2602.08324v3 Announce Type: replace Abstract: Chain-of-Thought (CoT) reasoning successfully enhances the reasoning capabilities of Large Language Models (LLMs), yet it incurs substantial computa

arXiv:2605.16087v1 Announce Type: cross Abstract: Deep Neural Networks have become the dominant solution for Autonomous Driving perception, but their opacity conflicts with emerging Trustworthy AI gui

arXiv:2605.15876v1 Announce Type: new Abstract: Vision-Language Models (VLMs) excel at 2D tasks such as grounding and captioning, yet remain limited in 3D understanding. A key limitation is their text

Ollama v0.30.0 is a pre-release version that changes the architecture to directly support llama.cpp instead of building on top of GGML, enables GGUF file format compatibility, and uses MLX to accelera

v0.30.0-rc18 is a pre-release version that changes Ollama's architecture to directly support llama.cpp instead of building on GGML, enabling GGUF file format compatibility. MLX is used to accelerate m

v0.30.0-rc19 is a pre-release version of Ollama that changes the architecture to directly support llama.cpp instead of building on GGML, enables GGUF file format compatibility, and uses MLX to acceler

arXiv:2505.18134v3 Announce Type: replace Abstract: Vision-language models (VLMs) have achieved strong results on coding and math benchmarks that are challenging for humans, yet their ability to perfo

arXiv:2504.05451v2 Announce Type: replace Abstract: Traditional methods for view-invariant learning rely on controlled multi-view training data with minimal scene clutter. However, they struggle with

Comfyui-Mesh now supports LTX 2.3 with the ability to distribute models across multiple GPUs or networked machines using Nvenc codec for video generation. The update includes significant VRAM optimiza

arXiv:2605.14949v1 Announce Type: new Abstract: Carotid atherosclerosis is a major contributor to ischemic stroke and transient ischemic attack. Conventional ultrasound assessment is commonly based on

arXiv:2510.19973v4 Announce Type: replace-cross Abstract: The path to higher network autonomy in 6G lies beyond the mere optimization of key performance indicators (KPIs), requiring systems that perce

arXiv:2601.03969v2 Announce Type: replace Abstract: Large reasoning models enhanced by reinforcement learning with verifiable rewards have achieved significant performance gains by extending their cha

arXiv:2506.01015v2 Announce Type: replace Abstract: Segment Anything Model 2 (SAM2) exhibits strong generalisation for promptable segmentation in video clips; however, its integration with the audio m

b9163 is a llama.cpp release that adds a custom Unicode regex handler for Qwen3.5's tokenizer to prevent stack overflows on long inputs . The release also includes improvements to SYCL memory manageme

b9172 is a release of llama.cpp that includes binaries for macOS, Linux, Android, Windows, and openEuler platforms with support for various hardware configurations including CPU, Vulkan, CUDA, ROCm, O

arXiv:2605.14146v1 Announce Type: new Abstract: bde is a user-friendly Python package for Bayesian Deep Ensembles with a particular focus on tabular data. Built on an efficient JAX implementation of t

arXiv:2605.14772v1 Announce Type: new Abstract: Understanding human motion beyond surface kinematics is crucial for motion analysis, rehabilitation, and injury risk assessment. However, progress in th

arXiv:2601.21174v2 Announce Type: replace Abstract: Entity alignment (EA) is critical for knowledge graph (KG) fusion. Existing EA models lack transferability and are incapable of aligning unseen KGs