omlab/VLX-Seek-1.5-10B · Hugging Face
VLX-Seek-1.5-10B VLX-Seek-1.5-10B is the open-source 10B model in the VLX-Seek 1.5 family, designed for fine-grained perception and visual grounding in embodied scenarios. It targets practical setting
Knowledge catalogue
VLX-Seek-1.5-10B VLX-Seek-1.5-10B is the open-source 10B model in the VLX-Seek 1.5 family, designed for fine-grained perception and visual grounding in embodied scenarios. It targets practical setting
arXiv:2608.06632v1 Announce Type: new Abstract: Industrial recommendation systems predominantly adopt a passive ranking paradigm that infers user preferences from implicit behavioral signals (e.g., cl
arXiv:2608.06959v1 Announce Type: new Abstract: Modern Earth observation (EO) satellites carry increasingly advanced sensors that produce vast volumes of high-resolution, multispectral data, yet downl
arXiv:2608.06630v1 Announce Type: new Abstract: Pruning reduces the inference cost of large language models, but existing criteria primarily preserve large activations or reconstruct layer outputs. We
Demand for low-precision inference, including NVFP4-based approaches, has grown as large language models are increasingly deployed in latency and cost constrained production environments. Quantization
Hey everyone, I constantly see high praise for M3 and M4 Macs for local LLM inference, even the base/16GB models. However, my experience has been quite different, and I'm trying to figure out if I hav
seems to be about as good as a vega 56 with 16Gb of VRAM, is it worth it? (don’t want to deal with NVIDIA drivers on Linux, already have an rx6650xt and might simply use vulkan for llamacpp inference)
arXiv:2608.05217v1 Announce Type: cross Abstract: Vision Transformers (ViTs) increasingly rely on input-adaptive inference, such as token pruning and early halting, to meet energy and latency budgets.
arXiv:2608.05784v1 Announce Type: new Abstract: Computer-use agents pay full frontier inference to re-derive routines their user has already performed, because an agent's memory today records what the
arXiv:2608.06362v1 Announce Type: cross Abstract: Deciding which of two agents is stronger means playing games until skill outweighs luck, and every game costs money, model inference, or expert time.
arXiv:2608.05448v1 Announce Type: new Abstract: Speculative decoding accelerates large language models' inference by using a lightweight drafter to propose multiple future tokens and a target model to
arXiv:2608.05780v1 Announce Type: new Abstract: Recent advancements in MLLM-based long-form video understanding have mitigated inference-time computational cost and limited context lengths by selectin
High-performance inference of NVIDIA's Parakeet TDT 0.6B V2 English transcription model, in the browser. Check out the live demo: https://parakeet.narcotic.sh/ A fully custom, dependancy-free implemen
arXiv:2608.05326v1 Announce Type: cross Abstract: Autoregressive large language model inference is increasingly constrained by the memory footprint of the Key-Value (KV) cache. A dominant line of work
arXiv:2608.05643v1 Announce Type: new Abstract: Test-time scaling improves LLM reasoning by using additional inference compute, but wider sampling alone can suffer from diminishing returns: new rollou
arXiv:2608.05156v1 Announce Type: new Abstract: Post-training of large language models optimizes only parameters, while inference-time procedural scaffolds are typically designed independently of para
arXiv:2602.14265v3 Announce Type: replace Abstract: Inference-Time-Compute (ITC) methods like Best-of-n and Tree-of-Thoughts are meant to produce output candidates that are both high-quality and diver
arXiv:2509.06861v3 Announce Type: replace Abstract: Test-time scaling increases inference-time computation through longer reasoning chains and has shown strong performance gains across many domains. H
arXiv:2608.06270v1 Announce Type: new Abstract: The 'thinking-with-images' paradigm equips multimodal LLMs with active visual operations such as crop-and-zoom. However, models using these operations o
arXiv:2608.06177v1 Announce Type: new Abstract: Binary neural networks are very attractive for constrained deployment, enabling small footprint and low-power inference. For binary activations, the dot
arXiv:2608.06241v1 Announce Type: new Abstract: Existing machine-learning weather forecasting models rely on predetermined and fixed autoregressive timesteps. The choice of model timestep involves a f
arXiv:2603.12617v2 Announce Type: replace-cross Abstract: Speculative decoding has emerged as a widely adopted paradigm for accelerating large language model inference, where a lightweight draft model
arXiv:2608.06057v1 Announce Type: new Abstract: Tool-calling agents infer task state from accumulated dialogue and tool traces. In persistent interactions, however, historical traces may remain struct
ci : onboard AMD ROCm CI with gfx1151 fixes (#26544) ci: prepare for amd rocm ci Signed-off-by: Aaron Teo aaron.teo1@ibm.com ci: fix editorconfig-checker Signed-off-by: Aaron Teo aaron.teo1@ibm.com ci
arXiv:2608.05103v1 Announce Type: new Abstract: Data assimilation (DA) uses Bayesian inference to update the state of a numerical forecast model with observed data. In this study, we propose a fundame
arXiv:2608.04483v1 Announce Type: new Abstract: Vision-language models (VLMs) process an image as a sequence of visual tokens, which creates a substantial computational bottleneck during inference. Re
arXiv:2602.11506v4 Announce Type: replace-cross Abstract: The transition toward localized intelligence through Small Language Models (SLMs) has intensified the need for rigorous performance characteri
arXiv:2608.04811v1 Announce Type: new Abstract: Structured pruning enhances the efficiency of deep neural networks (DNNs) by eliminating groups of parameters during inference. Previous methods mostly
arXiv:2608.04049v1 Announce Type: cross Abstract: The principle of Occam's razor, which instructs us to prefer simplicity in inductive inference, has attracted much scrutiny both in the philosophy of
arXiv:2608.04309v1 Announce Type: new Abstract: We present a structured large-language-model (LLM) architecture for zero-shot human--robot coordination in a cooperative construction task with private
arXiv:2608.03047v1 Announce Type: new Abstract: Generating natural-language coaching feedback on motor skills can accelerate learning, yet expert coaches are scarce and expensive. Existing reference-b
arXiv:2608.02901v1 Announce Type: cross Abstract: The key-value (KV) cache is the primary memory bottleneck in long-context LLM inference. Existing approaches attack it from opposite ends: eviction me
arXiv:2607.15065v2 Announce Type: replace-cross Abstract: Predictive world models enable robots to plan by imagining the outcomes of their actions, but their value for control hinges on generating man
arXiv:2608.03618v1 Announce Type: new Abstract: Inferring complete 3D geometry and semantics from onboard images remains challenging because occlusions and restricted fields of view leave large scene
arXiv:2608.03083v1 Announce Type: cross Abstract: Video large language models (VideoLLMs) achieve strong video understanding performance, but their inference remains expensive due to the large number
arXiv:2608.03917v1 Announce Type: new Abstract: Causal perception occurs when agents with competing Structural Causal Models (SCMs) of the same system infer different probability distributions, includ
arXiv:2608.03967v1 Announce Type: cross Abstract: Generative Flow Networks (GFlowNets) have emerged as a flexible framework for amortised inference over discrete and mixed discrete-continuous objects,
As you all know the model is 2.69B parameters with a 128K context window and purpose-built for multi-step agent workflows. What you are seeing is the Q4_K_M GGUF running on my own inference engine bui
arXiv:2606.15615v2 Announce Type: replace-cross Abstract: Diffusion Transformers with Mixture-of-Experts (DiT-MoE) improve model capacity under sparse activation, but diffusion inference is still bott
arXiv:2608.02700v1 Announce Type: cross Abstract: Analog compute-in-memory (CIM) enables energy-efficient neural network inference, but device variation and read noise can severely degrade low-bit qua
arXiv:2507.07754v3 Announce Type: replace-cross Abstract: Machine unlearning is usually evaluated by what the classifier outputs: forget-set accuracy, confidence, membership-inference scores. We show
arXiv:2608.04010v1 Announce Type: cross Abstract: Existing scaling strategies for Multimodal Large Language Models (MLLMs) typically expand either model parameters or sequential inference computation,
arXiv:2608.03611v1 Announce Type: new Abstract: Multimodal Sentiment Analysis (MSA) integrates text, audio, and vision to infer human affect, yet real-world multimodal observations are often incomplet
arXiv:2608.02893v1 Announce Type: cross Abstract: Counterfactual inference approaches for sequential decision-making typically assume deterministic causal models, where all randomness stems from laten
arXiv:2602.16611v3 Announce Type: replace-cross Abstract: Humans can infer material characteristics of objects from their visual appearance, and this ability extends to artistic depictions, where simi
arXiv:2608.03276v1 Announce Type: new Abstract: Long-context inference with large language models is constrained by the linear growth of the key-value cache to sequence length. While pruning offers mi
arXiv:2604.07635v2 Announce Type: replace-cross Abstract: This research considers a scalable inference for spatial data modeled through Gaussian intrinsic conditional autoregressive (ICAR) structures.
arXiv:2608.03902v1 Announce Type: new Abstract: Resource constraints on UAV platforms have driven a paradigm shift in aerial tracking, from pursuing performance toward balancing accuracy with efficien
arXiv:2608.02274v1 Announce Type: cross Abstract: Electric Vehicle Charging Systems (EVCSs) are increasingly connected with Internet of Things (IoT) devices, which improves charging intelligence but a
arXiv:2608.01269v1 Announce Type: new Abstract: Hierarchical Graph Retrieval-Augmented Generation (GraphRAG) organizes corpus knowledge at multiple levels of granularity, yet fixed context constructio
arXiv:2608.00101v1 Announce Type: cross Abstract: AI coding agents like GitHub Copilot, Claude Code, and Codex interleave multi-step LLM inference with tool execution, creating a workload different fr
arXiv:2501.13084v2 Announce Type: replace Abstract: Active inverse source localization and characterization (ISLC) in dynamic fields requires sequential decision making under partial observability, wh
arXiv:2608.00562v1 Announce Type: new Abstract: Autoregressive image generators are commonly pretrained with token-level cross-entropy under teacher forcing, yet evaluated by the distributional qualit
arXiv:2608.02229v1 Announce Type: new Abstract: Classical neural networks frequently produce overconfident predictions on ambiguous or out-of-distribution (OOD) data, a liability that grows with each
arXiv:2607.18082v3 Announce Type: replace Abstract: Rubric-based RL has recently shown promise in improving LLMs on open-ended tasks. A widely recognized limitation of rubric-based RL is limited explo
arXiv:2608.00110v1 Announce Type: new Abstract: 3D scene understanding requires reasoning about entity existence, spatial layout, and object relations, yet RGB images alone often provide insufficient
arXiv:2608.00793v1 Announce Type: new Abstract: Dynamic manipulation requires robots to infer target motion and respond promptly, yet existing World-Action Models (WAMs) typically condition only on th
arXiv:2608.02474v1 Announce Type: new Abstract: Audio-driven video generation (A2V) has achieved promising progress in synthesizing temporally coherent and audio-visually aligned videos, yet its infer
arXiv:2608.02365v1 Announce Type: cross Abstract: World Action Models (WAMs) couple robot action prediction with video world models. Existing WAMs with shared-backbone and Mixture-of-Transformers desi
arXiv:2607.09786v3 Announce Type: replace-cross Abstract: To curb overthinking and reduce inference costs, researchers now train reasoning models with penalties on chain of thought length. We find tha