Knowledge catalogue
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:2609.09692v1 Announce Type: new Abstract: Chain-of-Thought (CoT) prompting enables LLMs to perform explicit, step-by-step reasoning, creating opportunities for sophisticated autonomous robots. H
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:2609.10377v1 Announce Type: cross Abstract: Safety is a fundamental requirement for autonomous driving, yet existing end-to-end driving models still lack explicit risk-aware learning capacities.
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:2609.07316v2 Announce Type: new Abstract: Due to the proliferation of vehicle trajectory data enabled by advanced sensing technologies, path representation learning has become a pivotal task in
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:2609.09241v1 Announce Type: cross Abstract: Mixture-of-Experts (MoE) architectures have emerged as a powerful paradigm for scaling model capacity while preserving efficient inference in large fo
arXiv:2609.08186v1 Announce Type: new Abstract: The emergence of Chain-of-Thought (CoT) has established a robust foundation for Large Reasoning Models (LRMs). While deep reasoning is widely believed t
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
arXiv:2505.19333v2 Announce Type: replace Abstract: Current evaluations of Large Language Model (LLM) steering techniques focus on task-specific performance, overlooking how well steered representatio
“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:2609.10001v1 Announce Type: new Abstract: Few-shot medical image segmentation (FSMIS) seeks to delineate unseen structures from a small support set, but its standard formulation fixes task-defin
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:2609.07573v1 Announce Type: new Abstract: Multi-agent LLM deliberation has been explored as a scalable way to simulate public deliberation. For such simulations to be informative, persona agents
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:2609.10166v1 Announce Type: new Abstract: UAV target following in cluttered environments is inherently predictive: current-state followers can lag behind turns, choose blocked corridors, or trad
arXiv:2609.06036v1 Announce Type: new Abstract: Proposal-based controllers---learned policies, language-model planners, and other black-box generators---are increasingly deployed behind runtime verifi
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:2609.09793v1 Announce Type: cross Abstract: Directional ablation removes an aligned language model's ability to refuse by projecting a single 'refusal direction' out of the weights that write th
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:2609.06960v1 Announce Type: new Abstract: Invasive neural recordings provide high-fidelity measurements of brain activity, with signals such as intracranial EEG (iEEG) and intracortical spiking
I'm no one special. But after the mathematicians and OpenAI debacle I've decided to cancel all of my cloud AI subscriptions. I know that's radical and crazy by today's standards...as of five minutes a
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
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
It's time to call these end-of-the-world anti-AI messaging groups exactly what they are: Terror cells - They funnel and wash money from a few donors to smaller groups to obscure origin - insert sleepe
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:2508.05427v2 Announce Type: replace Abstract: Large language models (LLMs) are beginning to reshape how organic-synthesis workflows are represented, queried, planned, and connected to experiment
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
arXiv:2609.09299v1 Announce Type: new Abstract: Decision trees are prized for their interpretability and strong performance on tabular data, but popular greedy top-down induction algorithms can yield
arXiv:2601.17036v2 Announce Type: replace-cross Abstract: ArXiv recently prohibited the upload of unpublished review papers to its servers in the Computer Science domain, citing a high prevalence of L
arXiv:2602.19600v2 Announce Type: replace-cross Abstract: Many high-dimensional datasets concentrate near a low-dimensional structure embedded in the ambient space. Generative models for such data mus
arXiv:2609.07598v1 Announce Type: cross Abstract: Large language models (LLMs) increasingly shape communication, learning, work, creativity, and decision-making, yet social-science research on these d
May, damn it, not six weeks. Senior, not entry level. 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 k