Knowledge catalogue
In the video, user Joseph instructs Delta (an AI model) to switch its provider configuration to @ollama, a custom OpenAI-compatible service. The entire setup occurs automatically within the chat threa
arXiv:2610.20640v1 Announce Type: new Abstract: Global streamflow forecasting supports flood preparedness, yet data-driven models trained on reanalysis lose skill when driven by operational forecasts,
arXiv:2610.22331v1 Announce Type: new Abstract: Deep search agents solve knowledge-intensive tasks through long-horizon, multi-turn interactions, where assigning credit to individual search decisions
arXiv:2610.20685v1 Announce Type: new Abstract: Symbolic regression searches for an equation that explains observed data. Numerical error is commonly used to guide the search, but it alone can favor a
arXiv:2610.21977v1 Announce Type: new Abstract: Physics-informed Gaussian processes (GPs) provide a principled framework for scientific inference by expressing uncertainty over empirical measurements,
arXiv:2606.22305v2 Announce Type: replace Abstract: Large Language Models (LLMs) achieve remarkable reasoning capabilities through reinforcement learning (RL) post-training. However, existing RL post-
arXiv:2610.22084v1 Announce Type: cross Abstract: Neural networks offer critical adaptability for controlling complex systems where nominal modeling proves intractable. However, when offline-trained n
arXiv:2610.22322v1 Announce Type: cross Abstract: The capabilities of an agent swarm depend on both its individual members and how they coordinate. Yet existing multi-agent systems often train agents
arXiv:2610.22316v1 Announce Type: cross Abstract: Large language model (LLM)-based agents and multi-agent systems increasingly tackle complex tasks through long-horizon tool use and inter-agent collab
arXiv:2606.12733v3 Announce Type: replace Abstract: Privacy auditing provides an important safeguard by estimating the actual information leaked by a model, thus ensuring that theoretical privacy guar
arXiv:2610.21282v1 Announce Type: cross Abstract: Spatial augmented reality (SAR) augments physical environments with projected content, but most systems assume that the projector pose, target region,
arXiv:2606.13220v2 Announce Type: replace Abstract: Large language models (LLMs) are used for technical troubleshooting, where problem descriptions are often incomplete and multiple causes can explain
arXiv:2610.21254v1 Announce Type: new Abstract: Cyber threat intelligence (CTI) relies on the timely identification of emerging threats, enabling organizations and security analysts to support situati
arXiv:2610.20870v1 Announce Type: cross Abstract: We present a generative surrogate for charged-current (nu_mu)-nucleus scattering that can be calibrated to measured differential cross sections withou
arXiv:2610.21433v1 Announce Type: new Abstract: Diffusion models achieve high-quality image generation but remain computationally expensive due to iterative denoising across many timesteps. Existing a
arXiv:2610.20843v1 Announce Type: new Abstract: Map generation tasks feature extensive non-structural vectorized data (e.g., points, polylines, and polygons) and thus pose significant challenges to co
Tested the new MOSS-Image (5B single-stream DiT, Qwen3.5-9B text encoder, FLUX.2 VAE, Apache 2.0) on a plain RTX 3060 12 GB / 16 GB RAM with 35 deliberately hard prompts: dense on-image text in Englis
arXiv:2610.22086v1 Announce Type: cross Abstract: Supervised fine-tuning datasets remain overwhelmingly English-centric and commercially restricted, as their content is frequently generated by proprie
arXiv:2610.20881v1 Announce Type: new Abstract: While foundation models and vision transformers (ViTs) have redefined visual representations, current active learning (AL) strategies for these backbone
arXiv:2610.21108v1 Announce Type: new Abstract: LLM-based planning agents commit to plans of different lengths before interacting with a partially observable environment. Some aggressively commit to a
arXiv:2610.20628v1 Announce Type: new Abstract: Multi-agent systems (MAS) based on large language models (LLMs) have become a powerful way to address complex problems, and their effectiveness depends
arXiv:2610.22124v1 Announce Type: new Abstract: Modern agentic systems extend language models with external tools, enabling them to complete complex tasks through multi-turn interactions. As these age
arXiv:2610.21336v1 Announce Type: cross Abstract: We study sparse and continual reinforcement learning fine-tuning of language models through attention-head ranking and partitioning. For sparse learni
arXiv:2610.21709v1 Announce Type: cross Abstract: Robust covariance estimation under entry-wise contamination and missing data is challenging in various signal processing applications. Under the Stude
arXiv:2610.21214v1 Announce Type: new Abstract: Rubric-based evaluation is widely used to assess large language model (LLM) outputs by decomposing quality into multiple criteria and assigning each a b
arXiv:2610.21367v1 Announce Type: new Abstract: Test-time adaptation (TTA) mitigates the performance degradation of source-pretrained models on unlabeled test data under distribution shifts. Recent ba
arXiv:2610.22120v1 Announce Type: new Abstract: Knowing the layout of the physical world matters for many applications, yet the sensors we rely on for it (e.g., cameras and LiDAR) can fail in darkness
arXiv:2512.15756v2 Announce Type: replace-cross Abstract: Human-imposed design conventions can restrict the alternatives represented in scientific training data and shape the search preferences learne
arXiv:2610.21850v1 Announce Type: new Abstract: Generating 3D assets with explicit parts requires two properties at once: geometric detail inside each part and structural coherence across the whole ob
arXiv:2610.21393v1 Announce Type: new Abstract: Vehicle Routing Problems (VRPs) are fundamental to many real-world applications. Recent advances in large language models (LLMs) have spurred progress i
arXiv:2610.22369v1 Announce Type: new Abstract: Diffusion and flow models generate a sample over iterative steps, each a full pass through a large network, and that pass dominates generation cost. Tra
arXiv:2610.21621v1 Announce Type: new Abstract: Recent Vision-Language Models (VLMs) enable automated preference labeling for robotic manipulation, yet their deployment remains impractical since each
arXiv:2610.21114v1 Announce Type: cross Abstract: Post-hoc image explanations usually show where a model looks using spatial heatmaps or indicate which channels matter using global channel scores. The
arXiv:2609.12286v2 Announce Type: replace Abstract: Introducing large language models (LLMs) into evolutionary computation enables semantic generation of candidates, but the classical problem of maint
arXiv:2610.22071v1 Announce Type: new Abstract: Many hierarchical byte-level language models group bytes into patches using a learned boundary predictor whose view of the next codepoint depends on enc
arXiv:2604.03376v2 Announce Type: replace Abstract: Current work on radiology report evaluation has focused primarily on LLM-based metrics for chest X-rays (CXR), leaving open whether such approaches
arXiv:2610.21448v1 Announce Type: cross Abstract: In reinforcement learning, advantage-based value-learning methods, unlike standard Q-learning, share information across actions by decomposing the act
arXiv:2610.21128v1 Announce Type: cross Abstract: Label-free evaluation methods, such as self-consistency filtering, majority-vote aggregation, and agreement-based reliability scoring, rely on an impl
arXiv:2610.22370v1 Announce Type: new Abstract: Token merging has emerged as an effective training-free strategy for accelerating diffusion models by reducing redundant token computation while minimiz
arXiv:2610.19729v1 Announce Type: new Abstract: Monocular world-space human recovery methods excel on current benchmarks, but these rarely include fast camera motion. We introduce the K-Pop stress tes
arXiv:2610.18515v2 Announce Type: cross Abstract: Large language models (LLMs) increasingly act as personal assistants; however, little is known about how they capture national-level preferences on a
arXiv:2610.19656v1 Announce Type: new Abstract: Action-chunking vision-language-action (VLA) models predict sequences of future robot actions. Under fixed-horizon execution, the robot executes a fixed
arXiv:2610.14356v1 Announce Type: new Abstract: AI-enabled systems must remain dependable when the conditions under which they operate change (e.g., due to input perturbations, distribution shifts, or
arXiv:2610.19896v1 Announce Type: new Abstract: The reintegration of people in the workplace after an upper-limb injury is often a long process. Collaborative robots and humanoids operating in shared
arXiv:2610.14643v1 Announce Type: new Abstract: Clinical speech reveals identity through both spoken identifiers and voice, yet its pauses, delivery, and speaker roles can also carry useful clinical e
arXiv:2610.17410v1 Announce Type: new Abstract: Advances in large-scale machine learning have enabled agentic AI systems: persistent, autonomous computational entities that pursue goals, initiate acti
arXiv:2505.21055v2 Announce Type: replace Abstract: Large language model (LLM) agents have shown impressive reasoning capabilities in interactive decision-making tasks. These agents interact with envi
AI agent permissions determine what an agent is allowed to do on someone’s behalf. As agents get more powerful, we’re running into a basic problem: a model can’t reliably verify those permissions just
arXiv:2610.20141v1 Announce Type: new Abstract: In various industries, smoke and fire are two of the most important threats in the workplace. One of the common methods for detecting smoke and fire is
arXiv:2610.18449v1 Announce Type: new Abstract: AI agents for autonomous scientific discovery must decide which experiments to run under a limited budget. Most benchmarks for science agents provide fi
arXiv:2610.19685v1 Announce Type: cross Abstract: Supervised fine-tuning (SFT) changes logit margins among non-target tokens at teacher-forced prefixes. Matching a local reference distribution keeps t
arXiv:2610.19603v1 Announce Type: new Abstract: Transformers have demonstrated strong performance in long-term time series forecasting (LTSF), yet modeling non-stationary temporal dependencies remains
On October 15, 2026 the BG2 Pod hosted NVIDIA CEO Jensen Huang, who explored whether current AI revenue justifies large capital expenditures. The conversation identified 27 major bottlenecks limiting
arXiv:2610.15705v1 Announce Type: cross Abstract: India's Eighth Schedule recognises 22 languages, yet parallel data is uneven across them, and many language pairs, especially among lower-resource lan
arXiv:2610.18780v1 Announce Type: new Abstract: Large language model multi-agent systems extend individual agents' capabilities through collaboration across specialized roles, tools, and workflows. Ye
arXiv:2610.20293v1 Announce Type: cross Abstract: Large language models increasingly generate multiple retrieval actions jointly, while downstream systems often provide only one reward for the resulti
arXiv:2610.19778v1 Announce Type: cross Abstract: Computational compressive imaging, such as single-pixel imaging and lensless imaging, is a promising imaging technique, enabling the reconstruction of
arXiv:2610.18567v1 Announce Type: new Abstract: Retrieval-Augmented Generation (RAG) has emerged as a dominant paradigm for improving Large Language Model (LLM) by intertwining it with other component
arXiv:2610.16110v1 Announce Type: new Abstract: Ultra-short-term forecasting of densely distributed photovoltaic (PV) systems remains challenging because external meteorological and satellite products
arXiv:2610.19103v1 Announce Type: new Abstract: Group-based reinforcement learning enables large language model agents to learn from sparse outcome rewards in long-horizon tasks. Recent methods derive