Knowledge catalogue
arXiv:2603.11211v3 Announce Type: replace-cross Abstract: Incremental Learning (IL) aims to learn new tasks while preserving previously acquired knowledge. Integrating the zero-shot learning capabilit
arXiv:2608.11789v1 Announce Type: new Abstract: Knowledge distillation (KD) trains a compact student by attracting it towards a converged teacher. It is silent about which directions the teacher itsel
arXiv:2608.11499v1 Announce Type: cross Abstract: Task vectors enable model merging without joint retraining. In practice, the subset of task vectors to be merged may vary, but many existing methods u
arXiv:2608.11354v1 Announce Type: new Abstract: Modern recommender systems treat observed actions as reliable proxies for user preferences, yet interactions often reflect exploration or comparison rat
arXiv:2608.10367v1 Announce Type: new Abstract: Direct teleoperation of vehicles faces critical technical bottlenecks: communication latency and the operator's inability to physically perceive unmodel
arXiv:2608.10500v1 Announce Type: new Abstract: Creating photorealistic and temporally coherent animatable human avatars from RGB videos remains challenging. Current methods struggle to capture realis
arXiv:2608.10716v1 Announce Type: cross Abstract: Speech-to-speech (S2S) voice agents are increasingly being incorporated into enterprise for customer care and as daily companions for consumers owing
arXiv:2608.09939v1 Announce Type: cross Abstract: Production teams deploying LLM chat agents face a specific quality assurance gap: existing evaluation tools test individual responses or simulate soci
arXiv:2608.11027v1 Announce Type: cross Abstract: Benchmark leaderboards summarize how well a language model performs, but not how its behavior relates to that of other models or changes across genera
arXiv:2608.10699v1 Announce Type: cross Abstract: Text-Attributed Graphs (TAGs), endowed with abundant textual content along with topological structures, have emerged as a versatile backbone for real-
arXiv:2608.10157v1 Announce Type: new Abstract: Self-improving agents seek to reduce the human engineering effort behind AI systems by enabling them to evolve and self-improve their performance over t
arXiv:2510.13643v2 Announce Type: replace Abstract: Vision foundation models such as DINOv2 enable strong few-shot anomaly detection (FSAD) through simple non-parametric k-nearest-neighbor (k-NN) scor
arXiv:2608.09402v1 Announce Type: new Abstract: Simulation is crucial for developing and testing autonomous driving systems. In particular, the development of localization and control algorithms relie
Back after ~6 months — rebuilding my spiking language model around CPU-first inference Hey everyone. It’s been around six months since I last posted anything about this project here. Some of you might
arXiv:2603.26798v2 Announce Type: replace-cross Abstract: Vision-language model (VLM) encoders such as CLIP enable strong retrieval and zero-shot classification in a shared image-text embedding space,
arXiv:2608.08485v1 Announce Type: new Abstract: Current LLM safety guardrails face a fundamental tension: fine-tuning distorts pre-trained representations while generative judges incur prohibitive inf
arXiv:2608.07508v1 Announce Type: cross Abstract: Large language models are already advisors to millions of people of faith who bring them real decisions. The pressing question for a person of faith i
arXiv:2608.07958v1 Announce Type: new Abstract: Multimodal industrial anomaly detection has largely focused on discrete products using strongly correlated RGB and 3D observations, leaving continuous p
arXiv:2608.08612v1 Announce Type: cross Abstract: Recently, retrieval-augmented and memory-augmented methods have emerged as two promising paradigms for long-video question answering. However, existin
arXiv:2608.09885v1 Announce Type: new Abstract: The safety of large language model (LLM) agents depends not only on model weights but also on the agent harness that manages context, memory, tools, per
arXiv:2608.08282v1 Announce Type: new Abstract: Tool-using language-model agents face constraints whose meaning changes with observations and prior actions. We study exact sampling from the model dist
arXiv:2608.08627v1 Announce Type: new Abstract: Sparse mixture-of-experts (MoE) layers expand recommendation capacity through conditional computation, yet a trained checkpoint still stores and routes
I've been comparing Cline / Kilo / Qwen Code lately since they all handle long-task state differently. Cline: has Focus Chain, a markdown file kept outside the conversation that gets reinjected on a c
arXiv:2608.07107v1 Announce Type: new Abstract: World models are increasingly used to support planning in agents by predicting how environment states evolve in response to agent actions. Yet fluent ne
Meta returns to open weights: Muse Glimmer, its first open-weights release since Llama 4, scores 35 on the Artificial Analysis Intelligence Index. It is a 30B-parameter model, and the first from Meta
Motif-Technologies is one of the tech company participated South Korea's AI Foundation Model project.(독파모) Upstage(Solar Series), LG AI Research(EXAONE Series), and SKT(A.X Series) are the competitors
arXiv:2608.07251v1 Announce Type: cross Abstract: This paper documents an applied natural-language-processing framework for measuring the tone of Brazilian Monetary Policy Committee (Copom) statements
arXiv:2608.06919v1 Announce Type: new Abstract: LiDAR serves as a primary sensing modality for robots operating in outdoor environments. However, the performance of deep learning models in this domain
arXiv:2608.06031v1 Announce Type: new Abstract: Dynamic graph prompting freezes a pre-trained temporal backbone and adapts it to label-scarce downstream tasks using lightweight prompts. However, exist
arXiv:2608.05523v1 Announce Type: new Abstract: Predictive video models have emerged as promising world models by learning latent visual dynamics from large-scale video. Yet these models remain challe
arXiv:2608.06153v1 Announce Type: cross Abstract: Automated skill evolution enables Large Language Model (LLM) agents to continuously improve without expensive retraining. However, existing approaches
arXiv:2608.05243v1 Announce Type: cross Abstract: Factorized generative models commonly regularize a latent style variable z_s by matching its marginal distribution to a fixed Gaussian prior and inter
Moonlight & Mayhem (Raccoon Heist by Codex + GPT-5.6 Sol Ultra) On Wednesday I wrote about One-shotting a Raccoon Heist game using Claude Fable 5, where I had Claude Fable 5 build a full working game
I swear AA is not the bipartisan they so claim. An open source mode (Qwen 3.8 max) was number 1 on the agentic index, then they just so happen to launch 'v4.1.1' of their index in which they just adju
arXiv:2604.04444v2 Announce Type: replace Abstract: Open-vocabulary object detection (OVOD) enables models to detect any object category, including unseen ones. Benefiting from large-scale pre-trainin
arXiv:2608.05651v1 Announce Type: cross Abstract: Large language model (LLM)-driven evolution has shown promise for program search and algorithm discovery, but relying on strong models throughout long
arXiv:2608.06137v1 Announce Type: new Abstract: Tabular data are ubiquitous in real-world applications and are crucial for data-driven prediction and decision-making across science, industry, finance,
arXiv:2608.05563v1 Announce Type: cross Abstract: Self-evolving skill (SES) systems distill agent trajectories into persistent skills, allowing untrusted experience to become trusted instruction. We i
arXiv:2512.20113v4 Announce Type: replace Abstract: Subsurface delaminations in reinforced concrete bridge decks escape conventional visual inspection, and the two principal sensing techniques used to
arXiv:2608.04077v1 Announce Type: new Abstract: Evaluating financial AI agents requires criteria aligned with real professional work. Existing rubric methods typically derive criteria from task prompt
Just came across this coding benchmark: SciCode Artificialanalysis.ai reports a ranking which contradicts the feeling we've towards those models in real life coding. Is Gemma 4 really that good, or a
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:2608.04265v1 Announce Type: cross Abstract: Evaluations of LLM planning agents largely ask whether a task succeeds or a declared plan is followed. In strategic cyber-physical systems, a stronger
arXiv:2608.04183v1 Announce Type: new Abstract: When a language model follows an in-context conditional rule such as 'if P(x) then A else B,' does it assemble a runtime circuit with one module that te
arXiv:2608.02966v1 Announce Type: new Abstract: Most multiple-choice question (MCQ) benchmarks evaluate Large Language Models (LLMs) only by whether they select the correct answers. This binary scorin
arXiv:2608.03839v1 Announce Type: new Abstract: Training-free speculative decoding drafts by matching an exact suffix of the context against a pool of earlier context. That lookup misses correct draft
People continue to turn to outside AI education resources. Companies just aren't providing enough. I'm running a free AI Agent Workshop in a week with @mcuban for absolute beginners. 10,000+ people ha
arXiv:2608.04001v1 Announce Type: cross Abstract: Large language models can solve substantially harder reasoning problems with more inference-time compute. The term 'test-time scaling,' however, now c
To give some more context on what we are building with Daiwa Securities: During our technical verification phase, we integrated our AI agent technologies, specifically our AI Scientist and AB-MCTS fra
arXiv:2608.01014v1 Announce Type: new Abstract: Preference optimization improves mathematical reasoning in large language models (LLMs), but reliable chosen-rejected pairs usually require verified ans
arXiv:2608.01355v1 Announce Type: new Abstract: Decoding visual experience from non-invasive brain activity is central to neuroscience and brain-computer interfaces. Functional magnetic resonance imag
arXiv:2608.00491v1 Announce Type: new Abstract: Graph self-supervised learning aims to learn transferable representations from large-scale unlabeled graph data. Joint-embedding predictive architecture
arXiv:2602.07086v2 Announce Type: replace-cross Abstract: Enterprise software systems commonly expose business functionality through both relational databases and REST APIs. Accessing these interfaces
arXiv:2608.00285v1 Announce Type: new Abstract: Sixteen language models drawn from ten families produced, on average, the semantic diversity of 1.69 distinct formulations of a psychotherapeutic case,
arXiv:2608.01169v1 Announce Type: new Abstract: Streaming VideoLLMs process frames causally while visual tokens grow continuously, making compression essential for controlling prefilling latency and m
arXiv:2608.02217v1 Announce Type: new Abstract: Agentic multimodal reasoning extends passive image understanding by allowing VLMs to actively acquire and refine visual evidence through visual tool int
arXiv:2607.28818v1 Announce Type: new Abstract: As AI companions increasingly mediate repeated social interaction, users may rely on a stable role and shared history, yet locally acceptable replies do
arXiv:2607.28980v1 Announce Type: new Abstract: Graph Foundation Models (GFMs) have recently emerged as a promising paradigm for enabling knowledge transfer across diverse domains. Unlike traditional
arXiv:2607.29365v1 Announce Type: new Abstract: Graph Domain Adaptation (GDA) transfers predictive knowledge from labeled source graphs to unlabeled target graphs under distribution shift. Existing me
arXiv:2607.29011v1 Announce Type: new Abstract: Traversing crests, ledges, and ditches at high speed often launches vehicles into the air, and a mishandled landing presents a substantial crash hazard.