Knowledge catalogue
arXiv:2109.02355v2 Announce Type: replace-cross Abstract: The last decade of progress in machine learning (ML), especially the deep learning era, has raised a number of scientific questions that chall
arXiv:2609.10084v1 Announce Type: cross Abstract: Generalized zero-shot learning (GZSL) has emerged as an important paradigm for visual recognition systems that must generalize to classes that were no
arXiv:2609.09855v1 Announce Type: cross Abstract: Although probabilistic statements are ubiquitous, foundational disagreements persist about their understanding, as exemplified by debates between Baye
arXiv:2609.09492v1 Announce Type: new Abstract: Reinforcement learning has produced capable controllers across a broad range of legged-robot tasks, but a subset of these tasks fail to converge under s
arXiv:2609.10456v1 Announce Type: new Abstract: Nanoscale imaging of mammalian brains is critical for connectomics. X-ray laminography enables high-throughput imaging of extended, plate-like biologica
arXiv:2609.05837v1 Announce Type: new Abstract: LLM-based agents are increasingly deployed in real-world applications through tool-use APIs, yet training them for specific environments remains fundame
arXiv:2609.09187v1 Announce Type: cross Abstract: Advertising video generation is not only a video synthesis task, but also a product-conditioned reasoning problem whose success is measured by online
👇 All this Doom talk is a distraction from the fact that the big frontier AI companies (especially OpenAI) aren’t doing security competently. As an email I just got from longtime security engineer @Ni
arXiv:2609.07152v1 Announce Type: new Abstract: Goal-oriented conversational systems must answer factual questions, understand visitor-provided information, and advance business objectives without bec
arXiv:2609.09429v1 Announce Type: new Abstract: While accurate measurement of socioeconomic indicators remains challenging in data-scarce regions, which limits policy interventions and resource alloca
arXiv:2609.10193v1 Announce Type: cross Abstract: Protein-protein interaction (PPI) databases do not faithfully reflect biological realities. Instead, they are influenced by study and technical biases
arXiv:2609.10024v1 Announce Type: new Abstract: Robot Operating System 2 (ROS 2) standardizes application code against a middleware interface (RMW) whose reference implementations are built on the Dat
arXiv:2609.10036v1 Announce Type: cross Abstract: Large language model agents produce fluent action sequences across a wide range of tasks, yet they fail in characteristic ways once the environment be
arXiv:2602.14488v3 Announce Type: replace-cross Abstract: IR in low-resource languages remains limited by the scarcity of high-quality, task-specific annotated datasets. Manual annotation is expensive
arXiv:2505.13520v2 Announce Type: replace-cross Abstract: Textbook question answering (TQA) is a complex task, requiring the interpretation of complex multimodal context. Although recent advances have
arXiv:2609.05437v1 Announce Type: new Abstract: Previous AI alignment efforts have focused primarily on first-order social norms -- teaching models what is socially acceptable or unacceptable (e.g., `
arXiv:2609.09783v1 Announce Type: new Abstract: Asynchronous reinforcement learning has become the standard way to scale training for language models, but the resulting policy lag biases the critic to
arXiv:2609.08188v1 Announce Type: new Abstract: Vision-language models (VLMs) augmented with retrieval-augmented generation (RAG) benefit from access to external evidence. However, standard retrievers
arXiv:2408.10608v2 Announce Type: replace Abstract: Large language models (LLMs) may encode biased associations from heterogeneous training corpora that are not immediately visible under ordinary prom
arXiv:2609.10158v1 Announce Type: new Abstract: Generalized Category Discovery (GCD) assigns unlabeled instances, mixed with labeled data, to known or novel categories, requiring human-like compositio
common belief, for sure! but also, as i discuss in my (free) newsletter today, ridiculous, do you @peterwildeford actually believe it? see any holes in my argument! OpenAI employee says there's 70% ch
arXiv:2609.09597v1 Announce Type: new Abstract: Accurate contact prediction is useful for robotic manipulation only if it supports effective decisions. We investigate this connection using a compact,
arXiv:2609.10154v1 Announce Type: new Abstract: On-policy distillation (OPD) provides dense token-level supervision on student-generated trajectories. Although OPD performs strongly when teacher and s
arXiv:2507.21816v1 Announce Type: cross Abstract: Few-shot object detection (FSOD) for optical remote sensing images aims to detect rare objects with only a few annotated bounding boxes. The limited t
arXiv:2609.09235v1 Announce Type: cross Abstract: Choosing a deferral policy for a frozen classifier requires more than ranking uncertain cases: confidence may be miscalibrated, errors have unequal co
arXiv:2602.19574v2 Announce Type: replace-cross Abstract: Large-language-model (LLM)-based text-to-speech (TTS) systems can generate natural speech, but most are not designed for low-latency dual-stre
arXiv:2609.05529v1 Announce Type: cross Abstract: Large language model (LLM)-based multi-agent systems (MAS) predominantly rely on centralized orchestration and lack formal verification mechanisms for
arXiv:2609.10317v1 Announce Type: new Abstract: Streaming talking-head generation produces each frame as its driving audio arrives, yet fidelity and efficiency have so far pulled in opposite direction
arXiv:2609.09901v1 Announce Type: new Abstract: Large language models often repeatedly select the same answer even when many alternatives are plausible. Prior work treats this concentration as bias, b
arXiv:2609.10022v1 Announce Type: cross Abstract: Modern TTS systems approach human quality for high-resource languages but degrade when clean speech data is scarce. Modern Greek exemplifies this, lac
arXiv:2609.09536v1 Announce Type: cross Abstract: Average treatment effect (ATE) estimation in observational studies is a fundamental statistical tool used frequently in social science, medicine, and
arXiv:2609.09486v1 Announce Type: cross Abstract: Fairness auditing of text-to-image diffusion models often requires generating large numbers of images across sampling configurations, making comprehen
arXiv:2609.09788v1 Announce Type: new Abstract: Choosing when to retrain a deployed classifier requires assessing subgroup error rates across the sequence of models used, including periods between upd
“Everyone killed” still seems to me to be an unrealistic exaggeration; I still don’t see a plausible path to that. OpenAI and Anthropic researchers agree: their approach to AI development could get ev
arXiv:2609.09081v1 Announce Type: new Abstract: Mid-training, the stage between pre-training and alignment, is where a model's per-domain data composition is typically set by data availability rather
arXiv:2609.08267v1 Announce Type: new Abstract: Hallucination detection is crucial for large language models (LLMs), as hallucinated content creates significant barriers in applications requiring fact
arXiv:2602.13047v2 Announce Type: replace Abstract: Conversational speech reveals early signs of cognitive decline, including dementia and mild cognitive impairment (MCI). AI models show promise for s
arXiv:2609.08407v1 Announce Type: new Abstract: In this study, we identify depth-dependent prefix redundancy in final-readout LLM embedding models, notably across representative backbones including Qw
arXiv:2609.09905v1 Announce Type: cross Abstract: Preference alignment for flow and diffusion models now spans online reinforcement learning and offline preference optimization, but the relation betwe
Forty years ago the first worm 'escaped' containment and breached systems on the brand new Internet. It was illegal then and it's illegal now. If Anthropic and OpenAI are creating worms, labeling it '
arXiv:2609.05758v2 Announce Type: new Abstract: Conversational assistants can blend retrieval, action selection, escalation, and wording in a single model path, or separate those roles. We report a pr
arXiv:2609.10155v1 Announce Type: new Abstract: We approach a cognitive simulation perspective on episodic and semantic memory in multiple-choice question answering by incorporating text from individu
arXiv:2507.19364v3 Announce Type: replace Abstract: The integration of Large Language Models (LLMs) into social simulation has generated considerable enthusiasm, but also raises substantial methodolog
arXiv:2609.09213v1 Announce Type: new Abstract: We study how physical-state inputs affect a 0.8B hybrid language model adapted for manipulation with 6.2M trainable parameters. Six conditions are train
arXiv:2609.09808v1 Announce Type: new Abstract: Robotic manipulation tasks are often decomposed into behaviors or skills. However, one often needs to predefine these behaviors for specific tasks or tr
arXiv:2609.10225v1 Announce Type: new Abstract: Feature transformation improves predictive performance on tabular data by constructing informative abstractions from raw features. Recent generative app
arXiv:2609.06887v1 Announce Type: cross Abstract: Automated experimentation is most effective when the observables, available actions, and objective are defined before the experiment starts, as is the
// human-values.pseudo | ARTIFACT 0.1.0-experimental.1 | BASE 1.2.0-rc1 | EDITION ai-compact | NARRATOR System_Synthesis_Node_01 | PROVENANCE human-directed, AI-assisted | STATUS single-encoder resear
arXiv:2609.09953v1 Announce Type: new Abstract: Cross-lingual sentence encoders enable scalable transfer across hundreds of languages, powering applications such as translation mining and zero-shot le
arXiv:2609.07160v1 Announce Type: cross Abstract: Diffusion Large Language Models (dLLMs) generate text via bidirectional iterative denoising, naturally supporting user-specified constraints anchored
Incredible how people are making up different numbers of weeks/months for how long Coxon worked at Anthropic to assassinate his character. The only credible source (@MadisonMills22 @axios who spoke wi
arXiv:2609.09821v1 Announce Type: cross Abstract: Physics-based character control is a long-standing challenge in computer graphics and robotics, requiring policies that satisfy complex dynamics while
arXiv:2609.05975v1 Announce Type: cross Abstract: We introduce Chain of Intent, a governance framework for agentic AI at small regulated firms, and validate it against a failure it was built to addres
arXiv:2609.10292v1 Announce Type: new Abstract: Data augmentation is fundamental to training modern deep vision and multimodal models. While individual methods, such as RandAug, CutMix, Mixup, RandEra
Jacob was a senior researcher who joined Anthropic in May. My Anthropic colleagues and I had been trying to recruit him for ~2 years, because we knew he was a strong researcher at OpenAI. Before he le
arXiv:2609.09630v1 Announce Type: new Abstract: Standard behavior cloning supervises actions without explicitly constraining the future representation paired with each demonstrated action chunk. We in
arXiv:2609.10286v1 Announce Type: new Abstract: Humanoid locomotion on granular terrain remains a significant challenge due to its complex foot-terrain interaction dynamics that are difficult to model
arXiv:2609.10333v1 Announce Type: new Abstract: Uncertainty estimation for medical vision--language models (VLMs) using conformal prediction has gained increasing attention due to its distribution-fre
arXiv:2609.09234v1 Announce Type: cross Abstract: Vision-guided reinforcement learning for Unmanned Aerial Vehicles (UAVs) remains challenging due to unstable policy optimisation, aggressive explorati
arXiv:2609.09572v1 Announce Type: cross Abstract: Synthetic data has become a promising way to scale model training beyond limited human-generated data but it may also induce strong model collapse (Do