AI Can Learn Scientific Taste
arXiv:2603.14473v3 Announce Type: replace Abstract: Scientific discovery depends on expert judgement and foresight, which we call scientific taste: the ability to judge and propose research ideas with
Knowledge catalogue
arXiv:2603.14473v3 Announce Type: replace Abstract: Scientific discovery depends on expert judgement and foresight, which we call scientific taste: the ability to judge and propose research ideas with
arXiv:2608.18230v1 Announce Type: new Abstract: Looped language models improve reasoning and knowledge manipulation by applying shared computation repeatedly. Existing systems usually repeat an entire
arXiv:2608.18675v1 Announce Type: new Abstract: Accurate forecasting of energy consumption is important for the efficient operation of power systems, with direct implications for operational costs, en
AQuA's preprint uses 'recursive self-improvement' for a bounded research loop. It does not say the research-agent LM rewrites its own weights. The paper separates three objects: The language model dri
arXiv:2608.18575v1 Announce Type: new Abstract: Large language model (LLM)-based multi-agent systems (MAS) often exhibit complex failure modes, which frequently cause agents to produce incorrect outco
arXiv:2608.18938v1 Announce Type: new Abstract: Vision Language Models (VLMs) have recently emerged as a critical component of multimodal AI systems, enabling joint reasoning over visual and textual i
arXiv:2608.18578v1 Announce Type: new Abstract: Proactive interference (PI) is a documented failure mode in large language models in which retrieval of a repeatedly overwritten value degrades as prior
arXiv:2608.18613v1 Announce Type: new Abstract: Cyber threat intelligence (CTI) is increasingly consumed not by human analysts but by LLM agents that compose multi-step investigations at query time. T
arXiv:2608.18103v1 Announce Type: cross Abstract: Background: Mechanistic elucidation of traditional Chinese medicine (TCM) compound formulas remains a central challenge in the modernization of TCM. C
arXiv:2608.18488v1 Announce Type: cross Abstract: Social robots have been widely explored as tools for autism intervention, yet this literature has focused predominantly on children and has rarely inv
arXiv:2608.18685v1 Announce Type: new Abstract: Intelligent document processing (IDP) encompasses a broad range of tasks, including optical character recognition (OCR), document question answering (Do
arXiv:2608.18832v1 Announce Type: new Abstract: Audio-driven lip synchronization manipulates the mouth region of a talking-face video to match the driving audio while preserving head pose, identity, a
arXiv:2608.19047v1 Announce Type: new Abstract: We present Eureka, a task-conditioned Meta-Agent architecture that compiles long-horizon tasks into dynamic obligation graphs with explicit acceptance s
arXiv:2605.06185v2 Announce Type: replace Abstract: Large vision-language models perform well on short- and medium-length video understanding but still struggle to maintain coherent event memory and r
arXiv:2608.18736v1 Announce Type: new Abstract: Federated training enables language models to learn from distributed private text, but the server cannot directly verify the local supervision or optimi
arXiv:2608.18733v1 Announce Type: cross Abstract: We present Flama, an open-source Python framework for developing and deploying production-ready web APIs, machine learning services, and large-languag
arXiv:2608.19011v1 Announce Type: cross Abstract: Mechanisms for dynamically converting cyber threat intelligence (CTI) into actionable detection capabilities are necessary due to the rapid evolution
Howdy once again, I had a request to try out 5.3 on the benchmarks - they're unsaturated so it's a fun test right now! This one was interesting because I accidentally ran it on all 36 problems (rip 20
arXiv:2608.18767v1 Announce Type: new Abstract: Gradient matching attacks (GMAs) in LLM split learning (SL) rely on a critical yet underexplored assumption: the gradient exposed at the split interface
hey so im currently working to integrate a locally ran llm to control home assistant (through tool calling, no direct connection) so i can use a voice input without needing very specific commands. Its
Generative recommenders (GRs) replace traditional embedding‑based methods with transformer‑style sequence models like HSTU and Semantic IDs, addressing scalability, cold‑start, and long‑tail issues in
arXiv:2608.18184v1 Announce Type: new Abstract: Human-centric intelligence is evolving in the foundation-model era, with growing emphasis on scale, transferability, and general-purpose modeling. Yet i
I've been building AgentGraph Studio, a visual editor for designing multi-agent workflows and exporting them as runnable Python code. One thing I wanted to verify was whether the generated code actual
arXiv:2608.18957v1 Announce Type: new Abstract: Historical book collections contain rich visual elements - such as illustrations, photographs, engravings, and decorative art - that are frequently unde
I have a big database of local court decisions with a legal sentence which is like a paragraph summary of the doc. I've been tinkering with FTing for many days now, all results inconclusive never beat
arXiv:2601.01684v2 Announce Type: replace-cross Abstract: While dense retrieval models have been the standard for state-of-the-art information retrieval, their deployment is often constrained by high
arXiv:2608.19168v1 Announce Type: new Abstract: A single training example's contribution to a finished model is normally estimated rather than measured, because measuring it takes two expensive full p
arXiv:2608.18398v1 Announce Type: cross Abstract: Large language model (LLM) agents can now carry out long-horizon technical workflows involving complex tool use, code execution, file edits, and gener
AntLing has released the full six-checkpoint matrix for the Ling-3.0 base model. tiny: pretrained, mid-trained, WSM-merged flash: pretrained, mid-trained, WSM-merged The concrete artifact is six separ
Links: Preprint: https://doi.org/10.5281/zenodo.22028087 Entropic Scree Function v1.0.0 / GitHub: https://github.com/tjleestjohn/Entropic-Scree TL;DR: Standard PCA fundamentally fractures non-linear d
arXiv:2608.18419v1 Announce Type: cross Abstract: Recent work has shown that large language models (LLMs) exhibit strong numerical sequence modeling capabilities and show promise in time-series predic
arXiv:2608.18489v1 Announce Type: new Abstract: Knowledge graph question answering (KGQA) and knowledge-graph-based retrieval-augmented generation (KG-RAG) aim to ground answers in explicit graph evid
arXiv:2608.18274v1 Announce Type: cross Abstract: OpenAI Privacy Filter is a compact, bidirectional token-classification model for detecting and redacting personally identifiable information (PII) and
arXiv:2608.18360v1 Announce Type: cross Abstract: Agentic AI systems take consequential actions governed by more than one pre-action control at once: authority, resource, and evidence gates that can a
arXiv:2505.01783v2 Announce Type: replace Abstract: Online anomaly detection is essential in fields such as cybersecurity, healthcare, industrial monitoring, and telecommunications, where promptly ide
arXiv:2608.19098v1 Announce Type: cross Abstract: Multi-teacher on-policy distillation (M-OPD) has emerged as a promising paradigm for consolidating domain-specialized reinforcement learning (RL) expe
arXiv:2608.18573v1 Announce Type: new Abstract: Existing explainable deepfake forensic methods typically rely on task-adapted MLLM to jointly address detection, localization, and explanation. Inspired
arXiv:2608.19115v1 Announce Type: new Abstract: Modern pretrained encoders make representations from heterogeneous views increasingly reusable, but the procedure that determines view utility and combi
I benchmarked Qwen3.8-27B on MathArena/aime_2026 dataset, comparing BF16 and FP8 weights at medium and xhigh reasoning effort. Interesting findings are: quantized FP8 xhigh is better than BF 16 medium
arXiv:2608.18227v1 Announce Type: new Abstract: Push-T is an iconic benchmark for learning manipulation policies from human demonstrations. The robot must use a single point of contact to push a T-sha
arXiv:2608.18410v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models process long multimodal token sequences, making inference expensive in both memory and computation. Existing efficie
arXiv:2608.18140v1 Announce Type: new Abstract: We define an intertwined scheduling and routing problem where new jobs appear due to the degradation of the existing jobs. Specifically, once a job arri
arXiv:2608.18379v1 Announce Type: cross Abstract: When every candidate is wrong, correct-candidate selection is unavailable, yet the aggregation call can still solve the problem afresh. A correct aggr
arXiv:2608.19025v1 Announce Type: new Abstract: Accurately extracting nuanced, contextualized data from research articles is laborious and time intensive. Here, we investigate the performance of front
arXiv:2608.18545v1 Announce Type: new Abstract: Multilingual large language models often generalize across languages, and prior work suggests that their internal mechanisms can overlap cross-lingually
arXiv:2603.04448v2 Announce Type: replace Abstract: Current AI agents can flexibly invoke tools and execute complex tasks, yet their long-term advancement is hindered by the lack of systematic accumul
arXiv:2608.18532v1 Announce Type: new Abstract: Existing VLMs have achieved strong performance in video understanding, yet they struggle with long-video spatiotemporal reasoning when target objects be
arXiv:2608.18351v1 Announce Type: cross Abstract: Tool-using large language-model agents can complete a task while exercising authority that the user did not grant or the task does not need, causing e
arXiv:2605.05962v2 Announce Type: replace Abstract: This paper addresses end-to-end geospatial question answering over multilingual toponymic data. We introduce a bilingual (Russian-Tatar) dataset of
Twin1 AI Inc. launched today with 20 million in seed funding to build artificial intelligence-powered digital twins that carry an individual professional’s expertise across their organization. The San
arXiv:2608.18671v1 Announce Type: new Abstract: Egocentric video captures activities from the wearer's perspective, providing a direct view of human attention, hand--object interaction, and goal-direc
arXiv:2608.18186v1 Announce Type: cross Abstract: In the past few years, machine learning (ML) has been widely (and to an extent, successfully) implemented in medicine. However, uncertainties surround
Zero-trust security startup Zero Networks Ltd. today expanded its integration with Palo Alto Networks Inc., adding automated threat containment and a set of controls aimed at artificial intelligence a
arXiv:2511.17954v2 Announce Type: replace-cross Abstract: Incorporating spatial information, particularly when related to climate, weather, and demographic factors, is crucial for improving underwriti
arXiv:2606.12499v2 Announce Type: replace Abstract: We present AEM, an Action-Effect Memory pretraining framework for robot manipulation that learns compact temporal representations from vision-action
arXiv:2608.17310v1 Announce Type: new Abstract: Reinforcement Learning (RL) has been promising in single-turn LLM fine-tuning. However, long-horizon agentic reasoning introduces increasingly branching
I have been using local models on/off for like 2 years or so but never really used them extensively because the closed ones were always much better. Once Qwen 3.8 27B was released I decided to give it
None has undergone post-training, giving researchers flexible starting points for continued pre-training, fine-tuning, and further research. Two key highlights: - They use WSM to replace LR decay with
arXiv:2608.17856v1 Announce Type: new Abstract: Tabular prediction is a critical task across numerous applications. The recent success of large language models has sparked various approaches for adapt
arXiv:2503.20182v2 Announce Type: replace-cross Abstract: As large language models (LLMs) increasingly function as human-like assistants exhibiting human-like personality traits, understanding their b