Knowledge catalogue
First, kudos to Strata. It inspired this project, and while I was building it Strata got much faster and added NVFP4 support, which was my main reason for starting. By then I was too far in to stop, s
arXiv:2610.19525v1 Announce Type: cross Abstract: Verifiable instruction-following benchmarks emphasize output-constraint satisfaction but can overlook whether responses meaningfully answer the underl
arXiv:2610.18904v1 Announce Type: cross Abstract: A reading departs from what a monitoring system expects for one of three reasons: the physical process changed, the instrument is failing, or the valu
arXiv:2610.18880v1 Announce Type: new Abstract: High-throughput perturbation screens increasingly use machine-learning models to predict the effects of gene combinations that were never measured. A di
arXiv:2610.19302v1 Announce Type: new Abstract: On-policy distillation (OPD) provides dense token-level supervision on student rollouts, but this supervision can become unreliable when the student and
arXiv:2610.14625v1 Announce Type: new Abstract: Recursive self-improvement (RSI) offers a route to AI systems that participate in their own continued development. Recent methods allow language agents
arXiv:2610.14772v2 Announce Type: new Abstract: Camera-first agents must act on the visual world as it unfolds. We argue that the central obstacle for future camera-first agents is not recognition abi
arXiv:2610.18272v1 Announce Type: cross Abstract: Autonomous research agents must acquire and reason over evidence within a limited budget. Yet relevant sources can remain uninspected or unused, leavi
arXiv:2610.16182v1 Announce Type: new Abstract: Flagship large language models (LLMs) offer rich general knowledge and strong reasoning capabilities, but their high inference cost and latency limit th
arXiv:2610.15158v2 Announce Type: replace Abstract: We study neuro-symbolic natural language inference (NLI) with independently translated propositional representations of the premise and hypothesis.
arXiv:2610.19768v1 Announce Type: new Abstract: Looped transformers compute by applying one block repeatedly, so they can run for more loops than they were trained with. Recurrent reasoners are known
arXiv:2610.19571v1 Announce Type: new Abstract: Real-world engineering drawings are often large-format and information-dense. Answering practical engineering questions therefore requires both fine-gra
arXiv:2610.18092v1 Announce Type: new Abstract: Deep research (DR) agents address open-ended information needs through multi-step reasoning, long-horizon web search, and evidence synthesis. However, e
arXiv:2610.20256v1 Announce Type: new Abstract: Long-horizon agents must coordinate reasoning, tool use, and environment feedback over extended interactions. Learning from sparse outcome rewards requi
arXiv:2610.19679v1 Announce Type: cross Abstract: Large Language Model (LLM)-based agents have demonstrated remarkable capabilities in completing complex tasks through multi-step reasoning and tool in
arXiv:2610.14956v1 Announce Type: new Abstract: The Model Context Protocol provides a shared interaction substrate for the agentic web, allowing heterogeneous services to expose capabilities through a
arXiv:2509.09658v3 Announce Type: replace Abstract: Hallucinations in multimodal large language models (MLLMs), where a model generates content inconsistent with the input image, pose significant risk
arXiv:2610.20294v1 Announce Type: new Abstract: An agent can improve its behavior within an unresolved problem by changing how it acts and which experience it retains. We propose MMLA-RSI, a recursive
arXiv:2610.15292v1 Announce Type: new Abstract: LLMs increasingly support sensor-based human activity recognition (HAR) by linking motion signals with activity semantics and physical knowledge. Retrie
arXiv:2610.14636v1 Announce Type: new Abstract: Terminal rewards make multi-turn agents trainable without step-level annotations, but group-relative advantages provide little guidance about which inte
arXiv:2610.19314v1 Announce Type: new Abstract: Large language model (LLM) evaluators are increasingly used to assess personalized assistants, yet whether they can reliably judge personalization has r
arXiv:2606.22953v2 Announce Type: replace Abstract: Context managers summarize or evict old messages so agents can operate beyond a finite window. This creates a reliability problem: removing history
arXiv:2601.17226v3 Announce Type: replace-cross Abstract: Counterfactual storytelling exposes LLM shortcomings in causal reasoning, where few-shot prompting and SFT fail to produce logical and rationa
arXiv:2610.17728v1 Announce Type: new Abstract: Egocentric multimodal assistants see through the user's eyes and guide what the user does next, so their outputs directly shape physical actions, includ
arXiv:2506.04920v2 Announce Type: replace-cross Abstract: Large language models (LLMs) have demonstrated the ability to generate formative feedback and instructional hints in English, making them incr
arXiv:2610.19505v1 Announce Type: new Abstract: This paper proposes the SKG (Symplectic-Kernel Gradient) reasoning engine for law-induced inference and induction. Laws are a priori; data provide insta
arXiv:2601.07239v2 Announce Type: replace Abstract: Deterministic inference is a comforting ideal in classical software: the same program on the same input should always produce the same output. As la
arXiv:2610.20134v1 Announce Type: new Abstract: Tactile sensing is becoming central to robust, adaptive, and dexterous robotic manipulation. Beyond its traditional role in contact detection and reacti
arXiv:2610.19424v1 Announce Type: new Abstract: LLM system capabilities depend not only on model parameters but also on the executable harnesses that organize information acquisition, tool use, reason
arXiv:2610.20083v1 Announce Type: new Abstract: Visual world knowledge is a core capability of multimodal large language models (MLLMs), underpinning knowledge-intensive visual question answering and
arXiv:2610.19349v1 Announce Type: cross Abstract: Group Relative Policy Optimization (GRPO) provides no reward-relative learning signal when all rollouts receive identical rewards. In long-horizon tas
arXiv:2610.16324v1 Announce Type: new Abstract: Training-free language-based video anomaly detection (VAD) uses frozen vision--language models (VLMs) and large language models (LLMs) to localize abnor
arXiv:2610.17747v1 Announce Type: cross Abstract: Failure-attribution benchmarks ask an LLM judge which step or agent caused a failure. A high score should mean the judge checked the faulty step again
arXiv:2610.18656v1 Announce Type: new Abstract: Language model systems repeatedly make test-time decisions by comparing similarity: they retrieve exemplars, rank candidates, and revise responses. Yet
arXiv:2610.17824v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR) has become a principal recipe for improving the reasoning of large language models (LLMs). It rest
arXiv:2610.18874v1 Announce Type: cross Abstract: Agentic robotics places a large language model (LLM) agent in the robot control loop, where it composes perception, motion, and vision-language-action
arXiv:2606.15320v2 Announce Type: replace Abstract: Multimodal large language models have made rapid progress in video temporal grounding, yet real-world applications routinely require localizing ever
arXiv:2610.17114v1 Announce Type: new Abstract: Frontier large language models (LLMs) now reason about space well enough to program robots, yet the world models behind robot policies are implicit, hel
arXiv:2610.16172v1 Announce Type: new Abstract: Recent multimodal large language models (MLLMs) achieve strong results on video question answering, yet often fail to recover the temporal structure tha
arXiv:2511.20088v3 Announce Type: replace Abstract: In recent years, VAD (Visual Anomaly Detection) has attracted significant attention due to its high interpretability, as it provides visual explanat
arXiv:2610.18082v1 Announce Type: new Abstract: Long-horizon agents often struggle to recover from failures whose causes lie several steps earlier, beyond what local reflection or backtracking can res
arXiv:2610.16558v1 Announce Type: cross Abstract: World models capture environment dynamics and support counterfactual reasoning for planning. In image-goal navigation, where the target often lies bey
arXiv:2610.15398v1 Announce Type: new Abstract: Large language models (LLMs) demonstrate strong generalization across a broad range of reasoning and generation tasks, but their large parameter counts
This continues the small-model browser experiments from the previous posts. Two standard, off-the-shelf models ran locally on the same Samsung Galaxy S21: Gemma 4 E2B, Q3_K_M as the reasoner Qwen3.5-0
arXiv:2510.27114v2 Announce Type: replace-cross Abstract: Generative BC policies model expert action distributions well, but they do not explicitly reason about what scene a candidate action would pro
arXiv:2610.17246v1 Announce Type: new Abstract: Generative discovery in science requires coupling high-level scientific reasoning with the ability to generate samples respecting the structure of a des
arXiv:2610.18093v1 Announce Type: new Abstract: Wheel-legged robots operating in outdoor spaces shared with humans require accurate perception, socially compliant navigation, future-scene reasoning, a
arXiv:2610.17640v1 Announce Type: new Abstract: Spatial understanding is essential for embodied agents navigating and interacting with the physical world. As observations arrive incrementally, agents
arXiv:2610.15638v1 Announce Type: new Abstract: Knowledge graph (KG) foundation models (KGFMs) predict links on unseen graphs zero-shot. KGFMs have been pioneered by ULTRA which builds a relation grap
arXiv:2610.16902v1 Announce Type: cross Abstract: Bayesian Networks (BNs) are established tools for letting agents reason under uncertainty in sequential decision-making. They split a joint distributi
arXiv:2610.16895v1 Announce Type: cross Abstract: LLMs are used as high-level controllers for embodied agents, but it remains unclear whether they support collaborative reasoning, such as anticipating
arXiv:2610.16135v1 Announce Type: cross Abstract: Omni-modal large language models (Omni-LLMs) extend LLMs to process heterogeneous modalities (e.g., vision, audio, and IMU signals) alongside language
arXiv:2610.16444v1 Announce Type: new Abstract: Visual artifacts such as charts, technical diagrams, webpages, and document pages underpin scientific, commercial, and engineering workflows. Editing th
arXiv:2601.19060v2 Announce Type: replace Abstract: Multimodal Retrieval-Augmented Generation (MM-RAG) augments visual question answering (VQA) with external knowledge, but many systems rely on modula
arXiv:2601.13155v3 Announce Type: replace-cross Abstract: Long-context inference enhances the reasoning capability of Large Language Models (LLMs), but incurs significant computational overhead. Token
arXiv:2610.15742v1 Announce Type: new Abstract: Scene classification of remote sensing imagery with multimodal large language models (MLLMs) is formulated as a single-forward-pass decision problem: ca
arXiv:2610.18688v1 Announce Type: new Abstract: Agentic visual generation produces experience that can improve the native understanding (agent) and generation roles of a unified multimodal backbone, b
arXiv:2610.15854v1 Announce Type: new Abstract: Grounded spatial reasoning about indoor scenes rests on a geometric reconstruction that the multimodal system does not itself produce. Feed-forward mult
arXiv:2610.16533v1 Announce Type: cross Abstract: Reinforcement learning with verifiable rewards (RLVR) is reshaping how large language models (LLMs) acquire reasoning capabilities, yet the optimizers
arXiv:2610.18649v1 Announce Type: new Abstract: Message passing neural networks have shown remarkable performance in algorithmic and constraint reasoning, due to their ability to encode the structure