Knowledge catalogue
arXiv:2609.32193v1 Announce Type: new Abstract: Vision Language Action (VLA) models condition actions directly on current visual and language context, without an explicit account of how the scene evol
arXiv:2508.15641v2 Announce Type: replace Abstract: Precise temporal grounding requires distinguishing when a queried event occurs from when its participating entities are merely visible. We propose D
arXiv:2609.33803v1 Announce Type: new Abstract: Reward models underpin the alignment of large language models, yet the dominant designs reduce each prompt--response pair to a point estimate or to a di
arXiv:2609.34651v1 Announce Type: new Abstract: Generating high-quality UV textures for 3D meshes remains challenging. Multi-view projection pipelines suffer from occlusion and view inconsistency, and
arXiv:2605.06553v2 Announce Type: replace Abstract: Modern generative models can produce high-quality samples, but independent samples under the same condition often yields highly similar outputs. Par
arXiv:2609.33117v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) can now interpret a standard ten-second, twelve-lead electrocardiogram (ECG) with clinically grounded, reward-v
arXiv:2609.34893v1 Announce Type: new Abstract: Learning-based manipulation policies relying on RGB cameras often suffer from degraded observations under extreme exposure. Event cameras mitigate this
arXiv:2609.33762v1 Announce Type: cross Abstract: LLM agents resend their whole conversation on every turn, and most of it was already processed on the previous turn. Serving systems avoid recomputing
arXiv:2609.31638v1 Announce Type: new Abstract: Modern design optimization frameworks aim first and foremost for models with the most accurate predictions without balancing computational overhead. It
arXiv:2609.34817v1 Announce Type: new Abstract: Human dexterity is guided by two eyes watching two hands: binocular vision supplies the metric 3D structure that fine-grained manipulation consumes. Ego
arXiv:2603.20212v2 Announce Type: replace-cross Abstract: Reward models (RMs) are critical for aligning Large Language Models via Reinforcement Learning from Human Feedback (RLHF). While Generative Re
arXiv:2609.31715v1 Announce Type: new Abstract: Agentic recognition requires visual perception to move beyond static scene understanding and produce structured scene representations that support the p
arXiv:2609.34633v1 Announce Type: new Abstract: Long-term memory supports the self-evolution of LLM agents by retaining experience and skills across tasks and enabling their retrieval, reuse, and revi
Gentle reminder that Hugging Face was declined help from Anthropic & OpenAI models when they were being hacked by OpenAI models Self-hosted GLM 5.2 helped them protect themselves when the closed labs
arXiv:2609.32222v1 Announce Type: new Abstract: Raw 3D point clouds are a core geometric representation. Establishing their ownership is challenging because point sets are irregular, unstructured, and
arXiv:2412.08911v4 Announce Type: replace Abstract: Multi-objective learning endeavors to concurrently optimize multiple objectives using a single model, aiming to achieve high and balanced performanc
arXiv:2609.35738v1 Announce Type: cross Abstract: A language-model agent is jointly defined by its model and its harness, the executable program that organizes model calls, tool use, and information f
ninfer, dwarfstar, Splash, llamAmpere, gufo, etc. We've all seen them popping up, great tok/s, people loving them. Forks of llama.cpp or another engine, or made from scratch. For better or worse, the
🚨 JUST NOW: Elon Musk and Jensen Huang give an INSIDE LOOK at the big meeting between top AI firms and President Trump today, saying they'll now be 'grading each other's homework' 😆 @elonmusk: 'We sig
arXiv:2609.33423v1 Announce Type: new Abstract: Large Language Models (LLMs) can contribute useful engineering knowledge to robot design, but directly generated designs may rely on implicit assumption
arXiv:2609.35046v1 Announce Type: new Abstract: Category-level 6D pose estimation from a single RGB-D observation is inherently under-constrained, since partial visible geometry must be interpreted to
arXiv:2609.35573v1 Announce Type: new Abstract: Feed-forward novel view synthesis reconstructs a scene from many input images in a single forward pass, yet more views do not necessarily improve perfor
arXiv:2609.33521v1 Announce Type: new Abstract: Trust evaluation plays a critical role in cybersecurity by supporting risk mitigation and decision-making. A variety of trust evaluation methods have be
arXiv:2609.34427v1 Announce Type: new Abstract: Scaling LLM-based optimization from textbook-scale instances to real-world, industrial tasks remains a critical open challenge. Existing approaches are
arXiv:2609.35536v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) can explain deepfake verdicts in natural language, but such explanations are not necessarily visually grounded
arXiv:2609.34386v1 Announce Type: cross Abstract: On-policy distillation (OPD) uses teacher correction on student-generated responses. Full-vocabulary correction can provide important corrections even
arXiv:2609.34218v1 Announce Type: new Abstract: Looped language models separate computational depth from parameter count by repeatedly applying the same transformer block. Adapting these models requir
arXiv:2609.31644v1 Announce Type: new Abstract: Reinforcement learning (RL) is widely used in language-model post-training to maximize rewards assigned to individual model outputs, such as scores from
arXiv:2511.18038v2 Announce Type: replace-cross Abstract: Testing RESTful API is increasingly complicated but indispensable to quality assurance of cloud-native applications. This paper reports a mult
arXiv:2609.35515v1 Announce Type: cross Abstract: Scientific discovery requires not only recovering mathematical laws that describe observable behavior, but also identifying the mechanisms that genera
arXiv:2609.35431v1 Announce Type: new Abstract: This paper studies low-altitude question answering (LAQA), in which distributed unmanned aerial vehicle (UAV) memories are aggregated at a ground server
arXiv:2609.34330v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) have demonstrated impressive performance in multimodal understanding, but processing large numbers of visual to
arXiv:2609.31718v1 Announce Type: cross Abstract: Images often carry recommendation constraints that text metadata only hints at. A movie may need to look dark, a product may need a minimal style, and
arXiv:2603.10408v2 Announce Type: replace Abstract: The ultimate goal of video generation is to satisfy a fundamental trilemma: achieving high visual quality, maintaining rigorous physical consistency
arXiv:2609.35291v1 Announce Type: cross Abstract: Modern AI models are aligned through post-training to adapt them to downstream tasks. Recent work shows that fine-tuning language models on narrow tas
arXiv:2609.35338v1 Announce Type: new Abstract: Mechanistic discovery in neuronal microenvironments requires interventions and measurements that separate competing explanations of solute transport and
arXiv:2609.35052v1 Announce Type: new Abstract: Video world models must preserve the visual state of the world over time, but existing evaluation protocols often rely on generated histories, video ref
Oracle Corp. today is introducing an agentic software runtime that lets its Fusion applications carry out complex business tasks, from reconciling accounting entries to revising staffing plans when co
arXiv:2609.34985v1 Announce Type: new Abstract: Multi-reward policy optimization requires a joint update that reflects both the learning signals and the intended relationships among objectives. We int
arXiv:2609.31651v1 Announce Type: new Abstract: Historical manuscripts remain largely absent from modern vision-language benchmarks, leaving open how well multimodal large language models (MLLMs) hand
arXiv:2609.35303v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR) via Group-Relative Policy Optimization (GRPO) is widely used for multi-turn VLM agent training, ye
arXiv:2609.34605v1 Announce Type: new Abstract: Multi-teacher on-policy distillation (MOPD) has emerged as a popular post-training paradigm for integrating specialized capabilities in frontier languag
arXiv:2609.34415v1 Announce Type: new Abstract: The transition from Large Language Models (LLMs) to agents shifts safety stakes from toxic text to irreversible environmental harm. While current defens
arXiv:2609.34120v1 Announce Type: new Abstract: The majority of research on electricity consumption forecasting has focused on deterministic approaches, which generate a single point estimate for each
arXiv:2609.32469v1 Announce Type: cross Abstract: In-context learning is highly sensitive to demonstration choice, yet most methods select demonstrations using external query-demonstration similarity.
arXiv:2609.33088v1 Announce Type: new Abstract: Traditional change detection (CD) identifies changes between bi-temporal remote sensing images, while semantic change detection (SCD) assigns predefined
I'm running Qwen 3.8 27B Q4 XS with ~30 t/s decode (no MTP) at 100k context with q8/q5 KV cache on a 16GB AMD GPU. I wanted to share my setup since many believe Qwen 3.8 27B to be infeasible on 16GB V
arXiv:2609.33065v1 Announce Type: cross Abstract: Large language model (LLM) assistants can now search the web and consult external sources while completing user requests. These sources can provide us
arXiv:2609.32595v1 Announce Type: new Abstract: Safe and robust robot navigation across diverse environments requires a high-level understanding of complex scenes and the ability to carry it into stab
arXiv:2609.32516v1 Announce Type: cross Abstract: Security Operations Centers (SOCs) process large volumes of alerts daily. Alert triage prioritizes high-risk threats while reducing manual review of b
We have released Qwen3.8-Flash-Next quantized with GSQ and RCO, together with a second, capability-targeted build in which half of the model's experts have been removed. Flash-Next is a sparse mixture
arXiv:2609.35433v1 Announce Type: new Abstract: Reinforcement learning from verifiable rewards (RLVR) frequently reuses rollouts across multiple policy updates, increasing the mismatch between the cur
arXiv:2609.35469v1 Announce Type: cross Abstract: Autoregressive Vision-Language-Action (VLA) models offer a scalable path to robot learning, yet existing action tokenizers treat tokenization as a com
arXiv:2609.32444v1 Announce Type: new Abstract: We study training-inference mismatch in reinforcement learning with verifiable rewards (RLVR) for large language models, where rollouts are sampled by a
arXiv:2609.34210v1 Announce Type: new Abstract: Coding agents are beginning to move beyond purely digital tasks to tackle physical-world challenges, particularly in robotics. Existing robotics benchma
arXiv:2609.34556v1 Announce Type: cross Abstract: Transformers process tokens without any inherent notion of order, making positional encoding a fundamental requirement rather than an architectural re
arXiv:2609.34268v1 Announce Type: new Abstract: Large language models (LLMs) are now the default cognitive core of embodied household agents, yet the plans they emit are rarely checked against a groun
arXiv:2609.33126v1 Announce Type: new Abstract: Group-relative reinforcement learning (RL) relies on reward variation among sampled responses to estimate informative relative advantages. As language m
arXiv:2609.34235v1 Announce Type: new Abstract: Medical image segmentation remains challenging in practical deployment, as models often struggle to generalize beyond the distributions covered by their
arXiv:2609.34736v1 Announce Type: cross Abstract: Large language model (LLM) routing aims to select the most suitable model for each incoming query. Most existing routers learn this decision directly