Knowledge catalogue
Really interesting paper. I recommend it to anyone interested in training agents using existing harnesses. (bookmark it) ClawGym II runs RL through OpenClaw and Claude Code as opaque boxes. A serving
teams want to understand what their agents are doing but it’s hard to sift through all that trace data at scale but you can basically find any signal by fine-tuning a small, cheap model on data showin
arXiv:2608.15659v1 Announce Type: new Abstract: Learning to generate or reconstruct explorable worlds requires video paired with more than RGB: camera motion, scene geometry, temporal correspondence a
arXiv:2402.01591v4 Announce Type: replace-cross Abstract: Spatial sound reasoning is a fundamental human skill, enabling us to navigate and interpret our surroundings based on sound. In this paper we
arXiv:2608.14016v1 Announce Type: cross Abstract: Live game commentary is scarce: it exists for professional esports broadcasts and almost nowhere else. We present a content-based video narration syst
arXiv:2608.13773v1 Announce Type: cross Abstract: Neural networks are increasingly deployed in high-stakes applications with growing privacy leakage concerns. We show that this privacy leakage can occ
arXiv:2608.13565v1 Announce Type: new Abstract: Mixture-of-Experts (MoE) architectures scale large language models (LLMs) while preserving computational efficiency through sparse activation. Despite t
arXiv:2608.14191v1 Announce Type: cross Abstract: The key-value (KV) cache stores information from past tokens and is a major memory bottleneck in long-context inference. Existing quantization methods
arXiv:2608.14068v1 Announce Type: cross Abstract: Conversational recommendation for e-commerce is increasingly mediated by large language models (LLMs), yet many real-world deployments operate under a
arXiv:2608.13820v1 Announce Type: new Abstract: Composing independently trained adapters within a shared diffusion backbone provides a modular approach to multi-character generation, but naive joint d
Bloomberg reports Stripe agreed to buy model router OpenRouter for over $7B; Stripe has not confirmed the deal.
arXiv:2608.13511v1 Announce Type: new Abstract: Repeated in-situ evaluation of ocean-glider planners requires scarce vehicles, operators, deployment and recovery resources, and ocean conditions that c
arXiv:2608.13415v1 Announce Type: cross Abstract: We consider the problem of autonomously learning robot skills under a limited practice budget for sequential tasks. We propose an active skill learnin
arXiv:2608.12385v1 Announce Type: new Abstract: As large language models serve more requests, cumulative inference cost is becoming increasingly important relative to one-time training cost. The two i
arXiv:2608.12335v1 Announce Type: new Abstract: Financial question answering over annual reports requires more than retrieving semantically similar passages. It often involves identifying relevant com
arXiv:2608.12957v1 Announce Type: cross Abstract: Group Relative Policy Optimization (GRPO) learns from reward differences within a rollout group, but receives no useful relative signal when every sam
arXiv:2608.12915v1 Announce Type: cross Abstract: The rapid growth of LLM inference is shifting sustainability concerns from one-time training to continuous serving, where infrastructure decisions sha
arXiv:2608.12674v1 Announce Type: new Abstract: Maintaining price consistency and executing an Every Day Low Price strategy is critical for global retailers. However, with catalogs spanning millions o
arXiv:2608.13144v1 Announce Type: cross Abstract: As edge-side vision services continue to expand toward low-latency, high-throughput scenarios, reducing the inference cost of vision models without sa
arXiv:2608.13233v1 Announce Type: new Abstract: Manufacturing complex soft pneumatic actuators remains challenging because geometric fidelity, compliance, structural integrity, and airtightness must b
arXiv:2608.12721v1 Announce Type: new Abstract: Complex video object segmentation requires robust target propagation under severe occlusion, disappearance and reappearance. Although SAM3 provides stro
Computer History builds on the Chronicle research preview with reduced token usage and more privacy controls. A new timeline view gives you the ability to look back on your work and build skills from
arXiv:2602.02035v2 Announce Type: replace-cross Abstract: Multi-agent reinforcement learning systems deployed in real-world robotics applications face severe communication constraints that significant
arXiv:2603.02462v2 Announce Type: replace-cross Abstract: A key challenge in developing unified neural solvers for combinatorial optimization (CO) is the efficient generalization of models from a give
arXiv:2608.10765v1 Announce Type: new Abstract: Recognizing human behavior across levels of abstraction, from atomic actions to long-horizon intentions, requires data annotated along a semantic hierar
arXiv:2608.10441v1 Announce Type: cross Abstract: Many pipelines can pay a per-example cost to acquire an auxiliary, model-derived observation -- an LLM's structured reasoning, a slow oracle, an expen
arXiv:2608.10525v1 Announce Type: cross Abstract: Historical context integration presents a fundamental challenge for Vision-Language Models (VLMs) in sequential decision-making tasks. Current VLMs pr
arXiv:2512.05746v3 Announce Type: replace Abstract: Diffusion models have demonstrated significant applications in the field of image generation. However, their high computational and memory costs pos
arXiv:2608.11167v1 Announce Type: cross Abstract: Existing Multimodal Large Language Models (MLLMs) predominantly rely on image-text pairs for modality alignment pretraining, mapping global image repr
arXiv:2608.10416v1 Announce Type: cross Abstract: We present a theoretical foundation for inverse-distance attention, from its Euclidean prototype (Resolver) to its non-Euclidean realization (Riemann
arXiv:2608.11152v1 Announce Type: cross Abstract: Modern reinforcement learning (RL) post-training pipelines for large language models (LLMs) increasingly combine rollout workloads across multiple dom
arXiv:2608.10240v1 Announce Type: cross Abstract: Multi-modal sequential recommenders assume every item carries every modality, but real product catalogs often miss images or text, and a model trained
arXiv:2608.11024v1 Announce Type: new Abstract: Attribute hallucination---where vision-language models (VLMs) correctly identify an object but mischaracterize its properties---is prevalent yet mechani
arXiv:2608.09254v1 Announce Type: new Abstract: LLM analytics agents are evaluated on SQL syntax accuracy, but production failures look different: questions with two valid business definitions, questi
arXiv:2608.08131v1 Announce Type: cross Abstract: In the fictional Order 66, catastrophe does not arise from a powerful command alone: a trusted population is preconditioned, a short directive activat
arXiv:2608.07981v1 Announce Type: new Abstract: Streaming world models predict future visual states online while maintaining physically coherent dynamics over long horizons. However, their rollouts of
arXiv:2608.09536v1 Announce Type: new Abstract: High-quality document images are pivotal for information archiving and downstream automatic processing. However, they are frequently compromised by dive
arXiv:2608.07532v1 Announce Type: new Abstract: Modern agentic AI systems combine multiple large language model agents with heterogeneous skills, yet most architectures either fix communication in adv
arXiv:2608.09250v1 Announce Type: new Abstract: Federated learning (FL) must serve devices with varying computational capabilities. A fixed model cannot suit all devices, while training one model per
Artificial intelligence is a double-edged sword when it comes to cybersecurity. It is giving defenders new ways to sift through vast amounts of telemetry, identify anomalous behavior and automate rout
arXiv:2608.07579v1 Announce Type: cross Abstract: The AI City Challenge 2026 Track 1 evaluates multi-camera 3D perception in large indoor warehouses under a synthetic-to-real (Sim2Real) setting; depth
arXiv:2608.07520v1 Announce Type: cross Abstract: Mass religious gatherings such as the Kumbh Mela concentrate tens of millions of people into a single region over a few weeks, producing intense, repe
arXiv:2602.23290v2 Announce Type: replace Abstract: Extracting routable road networks from satellite imagery requires accurate topology recovery beyond pixel-level segmentation. Recent methods decompo
arXiv:2608.07427v1 Announce Type: new Abstract: LLM inference accounts for over 90% of AI operational energy, scaling directly with input token count---a critical inefficiency for telecom network anal
arXiv:2608.06471v1 Announce Type: cross Abstract: Despite recent advances, frontier large language model (LLM) agents remain limited in discovering and patching complex vulnerabilities in real-world s
arXiv:2608.07204v1 Announce Type: new Abstract: Scientific claim verification over a cited paper requires predicting the claim--paper relation and identifying the paragraphs that justify that predicti
arXiv:2608.06795v1 Announce Type: cross Abstract: Low-rank adaptation (LoRA) enables efficient specialization and distribution of large language models through compact adapters. However, untrusted ada
arXiv:2608.07088v1 Announce Type: cross Abstract: Multimodal large language models (MLLMs) encode images as long visual token sequences, making prefilling and KV-cache storage expensive. Existing trai
arXiv:2608.07063v1 Announce Type: cross Abstract: Content provenance standards, such as C2PA, are increasingly used to attach signed records of origin, editing history, and rights to digital images. H
I’m building DesktopLab, an open-source local-first control plane for development agents. I recorded the setup boundary that most agent demos skip: DesktopLab detects the host, proposes the supported
Modern Large Language Models achieve impressive reasoning capabilities with long Chain of Thoughts, but they incur substantial computational cost during inference, and this motivates techniques to imp
arXiv:2608.05254v1 Announce Type: new Abstract: Large language models can derive a plausible mathematical object yet still violate explicit requirements--for example, by omitting a modular reduction,
arXiv:2608.05303v1 Announce Type: cross Abstract: On-device deployment of Large Language Models (LLMs) has become essential for personalized edge applications. A primary bottleneck is external memory
arXiv:2608.05263v1 Announce Type: new Abstract: Multi-agent orchestration frameworks are moving from demos to production, yet benchmarks typically report task accuracy without diagnosing why a pipelin
arXiv:2608.05213v1 Announce Type: new Abstract: The style of a painting is not monolithic: color, texture, and structure may come from different sources. Existing reference-guided methods transfer the
arXiv:2608.04695v1 Announce Type: cross Abstract: Federated adaptation of time-series foundation models (TSFMs) is attractive for building energy forecasting because meter data are private, distribute
arXiv:2608.04568v1 Announce Type: new Abstract: As a key capability for embodied intelligence, 3D visual grounding (3DVG) has been predominantly studied in indoor scenes with RGB-D or point-cloud inpu
arXiv:2608.04896v1 Announce Type: new Abstract: Defensive driving scores are useful only when they preserve distinctions between policies that observe surrounding actors and those that do not. Re-simu
arXiv:2608.02989v1 Announce Type: cross Abstract: Speculative decoding verifies a tree of draft tokens in one target-model forward pass. For a mixture-of-experts (MoE) target, however, parallel verifi
arXiv:2608.03211v1 Announce Type: new Abstract: Visual world models typically learn future dynamics from a single observation stream, limiting their ability to model cooperative systems with multiple