Knowledge catalogue
arXiv:2610.19549v1 Announce Type: new Abstract: Graph retrieval-augmented generation (GraphRAG) uses document-derived knowledge graphs to assemble evidence for large language model (LLM) answers. Its
arXiv:2610.19100v1 Announce Type: cross Abstract: Constructing robust GUI agents relies on multimodal visual grounding: the ability to precisely map natural language intents to actionable on-screen co
arXiv:2610.20261v1 Announce Type: new Abstract: Deploying a general-purpose model as an agent means running it inside a product-specific runtime harness that decides which actions are executable, how
arXiv:2610.16125v1 Announce Type: new Abstract: An agent can retain successful trajectories without learning which part of an experience should repair a new discrepancy. We formulate passive imitation
arXiv:2610.19592v1 Announce Type: new Abstract: The ability to generate proteins with desired functions is a central goal of computational biology. Although natural language can express diverse design
arXiv:2610.18773v1 Announce Type: new Abstract: System one models enable direct, low-latency decision-making. Yet recent practice of predicting an answer from serialized text does not, by itself, resp
arXiv:2610.18616v1 Announce Type: cross Abstract: Searching text-rich knowledge graphs requires following relations while examining textual evidence. Predefined graph interfaces constrain what evidenc
arXiv:2610.15677v1 Announce Type: new Abstract: Continual learning aims to adapt pretrained large language models (LLMs) to evolving data while preserving their pretrained capabilities. A central chal
arXiv:2603.23784v1 Announce Type: cross Abstract: Grokking-the phenomenon where validation accuracy of neural networks on modular addition of two integers rises long after training data has been memor
arXiv:2610.20582v1 Announce Type: new Abstract: Long contexts enlarge key--value (KV) caches, increasing memory use and attention costs during generation. Compressing these caches must preserve inform
arXiv:2610.14573v1 Announce Type: new Abstract: Execution is often used as terminal feedback: it scores a generated program, but the resulting state is not used for another learning action. Learning a
arXiv:2610.16231v1 Announce Type: new Abstract: As large language models are increasingly adopted as multi-party communication facilitators, there is a growing demand for agents capable of balancing d
arXiv:2610.19165v1 Announce Type: cross Abstract: Many real-world questions demand not a single fact but an organized collection of them, yet existing factual knowledge benchmarks almost exclusively t
arXiv:2308.12241v2 Announce Type: replace-cross Abstract: Recently, the fast development of Large Language Models (LLMs) such as ChatGPT has significantly advanced NLP tasks by enhancing the capabilit
arXiv:2604.00477v2 Announce Type: replace Abstract: LLM-based agent judges are an emerging approach to evaluating conversational AI, yet a fundamental uncertainty remains: can we trust their assessmen
arXiv:2610.14071v1 Announce Type: cross Abstract: As LLM agents are increasingly deployed in high-stakes enterprise settings, understanding how they handle sensitive information in agentic dialogue ha
arXiv:2610.20570v1 Announce Type: new Abstract: Brazilian Portuguese remains underserved by open-source language models, and the few that are safety-aligned rarely document what did not work or valida
arXiv:2610.19443v1 Announce Type: new Abstract: Native multimodal pre-training trains a single model from scratch on text and multimodal data, enabling it to understand both language and visual inputs
arXiv:2610.20172v1 Announce Type: cross Abstract: Full-duplex speech systems must decide when to enter, hold, or relinquish the conversational floor, even as multiple speakers overlap or backchannel w
arXiv:2610.19215v1 Announce Type: new Abstract: Large language models are increasingly deployed as teams of agents that hold different private information about a shared task. How should such agents c
NVIDIA’s Nemotron 3.5 Super VL is now available to run on the Together AI compute platform through an API. The model page—providing pricing, benchmarks, and documentation—is hosted at together.ai/mode
Nemotron-3.5-Embed-1B-BF16 is a versatile embedding model developed by NVIDIA for multimodal and multilingual question-answering retrieval. The model can embed a document page in the form of an image,
arXiv:2610.19857v1 Announce Type: new Abstract: Recovering 3D human motion from sparse wearable sensors is challenging due to the inherent noise, occlusion, and instability of real-world tracking sign
arXiv:2610.18538v1 Announce Type: cross Abstract: Understanding agent heterogeneity can inform the design of shared and agent-specific policy representations, however existing criteria provide no unif
NVIDIA today released Nemotron 3.5 Super VL, an open 120-billion-parameter model that delivers the fastest task completion and highest accuracy for specialized always-on agents. Joining it are two new
arXiv:2610.20560v1 Announce Type: cross Abstract: 3D object composition is pivotal to digital content creation and robot simulation, while also serving as a critical testbed for physical intelligence
arXiv:2610.18755v1 Announce Type: cross Abstract: Reinforcement learning (RL) from unit tests is the common recipe for post-training code models, but a unit test only asks whether the final program pa
arXiv:2610.20538v1 Announce Type: new Abstract: Multimodal code intelligence connects the symbolic world of programs with the visual world their execution creates. Interest in this capability is burge
arXiv:2606.13349v2 Announce Type: replace Abstract: Effective peer review requires adaptive investigation that responds to evidence emerging from each paper. Existing LLM-based reviewers largely organ
arXiv:2610.15685v1 Announce Type: new Abstract: Conventional distillation transfers capability through teacher-generated demonstrations. LLM-as-a-Judge knowledge distillation offers a distinct and inc
arXiv:2610.18143v1 Announce Type: new Abstract: Prefix reuse improves LLM inference by sharing the KV cache of common prompt prefixes. This helps only if the scheduler can execute a matched branch in
arXiv:2610.15897v2 Announce Type: cross Abstract: Qwen3-8B reviewing Llama-3.1-8B in math adds 33.2 points, yet Qwen3-8B alone is 6.4 points more accurate than the result. Reviewing another model's an
arXiv:2610.03966v2 Announce Type: replace Abstract: Each run of an AI-driven research system (ADRS) is an expensive search over a vast solution space, and dependable evaluation requires many runs, mak
arXiv:2610.20091v1 Announce Type: new Abstract: Video scene graph generation (VidSGG) aims to capture objects and their evolving relationships in videos. This requires accounting for both the persiste
arXiv:2610.14299v1 Announce Type: cross Abstract: Recent Speech Full-Duplex (FDX) models are capable of engaging in naturalistic conversation by listening and speaking at the same time. Building on th
arXiv:2610.19431v1 Announce Type: new Abstract: This paper presents S^3-Nav, a structured spatial-semantic decision-making framework for language-guided robot navigation under partial observability. R
arXiv:2610.19869v1 Announce Type: cross Abstract: We introduce SEA-HELM Audio, a Southeast Asian (SEA) multilingual evaluation framework that extends the text-based SEA-HELM benchmark to assess perfor
arXiv:2610.19366v1 Announce Type: cross Abstract: Multimodal models and agents have emerged to enable AI systems to learn from and interact with the real world more like humans by integrating informat
arXiv:2610.19102v1 Announce Type: new Abstract: Aerial and remote sensing video is increasingly evaluated like web video, by posing multiple-choice questions to multimodal large language models (MLLMs
arXiv:2507.14843v5 Announce Type: replace-cross Abstract: Recent advances highlight Reinforcement Learning with Verifiable Rewards (RLVR) as a promising approach to enhancing LLM capabilities. However
The sudden collapse of the value of CoT (even summarized CoT) in the agentic era changes working with AI. Effectively steering AIs and getting any sort of observability now requires you to ask for int
arXiv:2610.19387v1 Announce Type: new Abstract: Identification and ranking of salient propositions in documents is indirectly involved in many AI tasks, but few papers define proposition salience scor
arXiv:2610.19041v1 Announce Type: cross Abstract: Understanding the dynamics of language acquisition in Large Language Models (LLMs) is crucial for uncovering how statistical representations evolve in
arXiv:2610.18617v1 Announce Type: new Abstract: An embodied agent must prioritise among competing bodily needs. In active inference, it can respond to an urgent need by increasing the precision of inf
arXiv:2610.18704v1 Announce Type: new Abstract: In this paper, we propose an extremely efficient, training-free method to extract token-level reward signals directly from an existing deep reward model
arXiv:2610.17723v1 Announce Type: new Abstract: People act on evaluative judgments produced by LLM agents, and in multi-agent systems those judgments pass through several agents before reaching a pers
arXiv:2610.14709v1 Announce Type: cross Abstract: Large language models are increasingly deployed in applications that act on users' long-term behavior histories, from personal assistants to recommend
arXiv:2610.16979v1 Announce Type: cross Abstract: Generative retrieval (GR) offers a promising paradigm for industrial search by unifying candidate generation within an autoregressive framework. Howev
arXiv:2610.16325v1 Announce Type: new Abstract: When a steering intervention changes a language model's behavior, which part of the intervention deserves the credit? We test this question for a target
arXiv:2610.19324v1 Announce Type: new Abstract: In large language models (LLMs), attention concentrates heavily on the first token. This 'attention sink' is believed to protect deep models against ove
arXiv:2610.10226v2 Announce Type: replace-cross Abstract: Can AI make Software Engineering (SE) -- the discipline -- obsolete? And can it make software engineers -- the professionals -- redundant? Thi
arXiv:2610.15666v1 Announce Type: new Abstract: Converting natural-language instructions into executable action plans conditioned on a scene image is a core capability for embodied human-robot interac
arXiv:2610.15343v1 Announce Type: new Abstract: World models and video understanding models are increasingly deployed in dynamic visual environments, yet their robustness to physical adversarial threa
arXiv:2610.14210v1 Announce Type: cross Abstract: ScanRefer Multiple queries require spatial disambiguation: several instances of the target class are present, and the referencer must pick one. When p
arXiv:2610.14155v1 Announce Type: cross Abstract: Reliable manipulation requires policies that generalize across tasks, layouts, and object interactions. Vision-language-action (VLA) models combine pr
arXiv:2610.15330v1 Announce Type: new Abstract: Accurate brain tumor segmentation from magnetic resonance imaging (MRI) is essential for diagnosis and treatment planning; however, manual delineation i
arXiv:2610.14746v1 Announce Type: cross Abstract: World Action Models (WAMs) commonly couple video and action experts through dense, layer-wise Mixture-of-Transformers (MoT) attention, exposing action
arXiv:2610.16293v1 Announce Type: new Abstract: Garment manipulation requires inferring both garment identity and complete configuration from partial, self-occluded observations. This creates a chicke
arXiv:2610.17532v1 Announce Type: new Abstract: Cross-species portrait animation, which aims to animate a source portrait of species A using a driving video of species B, is particularly challenging d
arXiv:2610.15185v1 Announce Type: new Abstract: Test-time memorization of sequential information is a foundational capability for any intelligent system that needs to rapidly store and retrieve data,