Long-term temporal information is crucial for event-based perception tasks, as raw events only encode pixel brightness changes. Recent works show that when trained from scratch, recurrent models achieve better results than feedforward models in these tasks. However, when leveraging self-supervised pre-trained weights, feedforward models can outperform their recurrent counterparts. Current self-supervised learning (SSL) methods for event-based pre-training largely mimic RGB image-based approaches. They pre-train feedforward models on raw events within a short time interval, ignoring the temporal information of events. In this work, we introduce TESPEC, a self-supervised pre-training framework tailored for learning spatio-temporal information. TESPEC is well-suited for recurrent models, as it is the first framework to leverage long event sequences during pre-training. TESPEC employs the masked image modeling paradigm with a new reconstruction target. We design a novel method to accumulate events into pseudo grayscale videos containing high-level semantic information about the underlying scene, which is robust to sensor noise and reduces motion blur. Reconstructing this target thus requires the model to reason about long-term history of events. Extensive experiments demonstrate our state-of-the-art results in downstream tasks, including object detection, semantic segmentation, and monocular depth estimation. Project webpage: https://mhdmohammadi.github.io/TESPEC_webpage.

Commercial LLM services often conceal internal reasoning traces while still charging users for every generated token, including those from hidden intermediate steps, raising concerns of token inflation and potential overbilling. This gap underscores the urgent need for reliable token auditing, yet achieving it is far from straightforward: cryptographic verification (e.g., hash-based signature) offers little assurance when providers control the entire execution pipeline, while user-side prediction struggles with the inherent variance of reasoning LLMs, where token usage fluctuates across domains and prompt styles. To bridge this gap, we present PALACE (Predictive Auditing of LLM APIs via Reasoning Token Count Estimation), a user-side framework that estimates hidden reasoning token counts from prompt-answer pairs without access to internal traces. PALACE introduces a GRPO-augmented adaptation module with a lightweight domain router, enabling dynamic calibration across diverse reasoning tasks and mitigating variance in token usage patterns. Experiments on math, coding, medical, and general reasoning benchmarks show that PALACE achieves low relative error and strong prediction accuracy, supporting both fine-grained cost auditing and inflation detection. Taken together, PALACE represents an important first step toward standardized predictive auditing, offering a practical path to greater transparency, accountability, and user trust.

Large language models (LLMs) have been increasingly deployed as local agents on personal devices with CPUs, NPUs and integrated GPUs. However, forecasting inference performance on devices with such heterogeneity remains challenging due to the dynamic compute and memory demands. Existing approaches rely on GPU benchmarking or machine learning-based latency predictors, which are often hardware-specific and lack generalizability. To this end, we introduce LIFE, a lightweight and modular analytical framework that is comprised of modular analytical model of operators, configurable to characterize LLM inference workloads in a hardware and dataset-agnostic manner. LIFE characterizes the influence of software and model optimizations, such as quantization, KV cache compression, LoRA adapters, chunked prefill, different attentions, and operator fusion, on performance metrics such as time-to-first-token (TTFT), time-per-output-token (TPOT) and tokens-per-second (TPS). LIFE enables performance forecasting using only hardware specifications, such as TOPS and memory bandwidth, without requiring extensive dataset benchmarking. We validate LIFE's forecasting with inference on AMD Ryzen CPUs, NPUs, iGPUs and NVIDIA V100 GPUs, with Llama2-7B variants, demonstrating the utility of LIFE in forecasting LLM performance through lens of system efficiency to enable efficient LLM deployment across different hardware platforms.

Judgment of risk is key to decision-making under uncertainty. As Daniel Kahneman and Amos Tversky famously discovered, humans do so in a distinctive way that departs from mathematical rationalism. Specifically, they demonstrated experimentally that humans accept more risk when they feel themselves at risk of losing something than when they might gain. I report the first tests of Kahneman and Tversky's landmark 'prospect theory' with Large Language Models, including today's state of the art chain-of-thought 'reasoners'. In common with humans, I find that prospect theory often anticipates how these models approach risky decisions across a range of scenarios. I also demonstrate that context is key to explaining much of the variance in risk appetite. The 'frame' through which risk is apprehended appears to be embedded within the language of the scenarios tackled by the models. Specifically, I find that military scenarios generate far larger 'framing effects' than do civilian settings, ceteris paribus. My research suggests, therefore, that language models the world, capturing our human heuristics and biases. But also that these biases are uneven - the idea of a 'frame' is richer than simple gains and losses. Wittgenstein's notion of 'language games' explains the contingent, localised biases activated by these scenarios. Finally, I use my findings to reframe the ongoing debate about reasoning and memorisation in LLMs.

Foundation models for natural language processing have many coherent definitions of hallucination and methods for its detection and mitigation. However, analogous definitions and methods do not exist for multi-variate time-series (MVTS) foundation models. We propose new definitions for MVTS hallucination, along with new detection and mitigation methods using a diffusion model to estimate hallucination levels. We derive relational datasets from popular time-series datasets to benchmark these relational hallucination levels. Using these definitions and models, we find that open-source pre-trained MVTS imputation foundation models relationally hallucinate on average up to 59.5% as much as a weak baseline. The proposed mitigation method reduces this by up to 47.7% for these models. The definition and methods may improve adoption and safe usage of MVTS foundation models.

This article explores the integration of AI-generated subject terms into library cataloging, focusing on validation through the Library of Congress Linked Data Service. It examines the challenges of traditional subject cataloging under the Library of Congress Subject Headings system, including inefficiencies and cataloging backlogs. While generative AI shows promise in expediting cataloging workflows, studies reveal significant limitations in the accuracy of AI-assigned subject headings. The article proposes a hybrid approach combining AI technology with human validation through LOC Linked Data Service, aiming to enhance the precision, efficiency, and overall quality of metadata creation in library cataloging practices.

In biomedical science, review by a Research Ethics Committee (REC) is an indispensable way of protecting human subjects from harm. However, in social science and the humanities, mandatory ethics compliance has long been met with scepticism as biomedical models of ethics can map poorly onto methodologies involving complex socio-political and cultural considerations. As a result, tailored ethics training and support as well as access to RECs with the necessary expertise is lacking in some areas, including parts of Europe and low- and middle-income countries. This paper suggests that Generative AI can meaningfully contribute to closing these gaps, illustrating this claim by presenting EthicAlly, a proof-of-concept prototype for an AI-powered ethics support system for social science and humanities researchers. Drawing on constitutional AI technology and a collaborative prompt development methodology, EthicAlly provides structured ethics assessment that incorporates both universal ethics principles and contextual and interpretive considerations relevant to most social science research. In supporting researchers in ethical research design and preparation for REC submission, this kind of system can also contribute to easing the burden on institutional RECs, without attempting to automate or replace human ethical oversight.

Artificial intelligence (AI) systems are evolving beyond passive tools into autonomous agents capable of reasoning, adapting, and acting with minimal human intervention. Despite their growing presence, a structured framework is lacking to classify and compare these systems . This paper develops a typology of agentic AI systems, introducing eight dimensions that define their cognitive and environmental agency in an ordinal structure. Using a multi - phase methodological approach, we construct and refine this typology, which is then evaluated through a human - AI hybrid approach and further distilled into constructed types. The framework enables researchers and practitioners to analyze varying levels of agency in AI systems. By offering a structured perspective on the progression o f AI capabilities, the typology provides a foundation for assessing current systems and anticipating future developments in agentic AI.

Large Language Models (LLMs) are revolutionizing industries by enhancing efficiency, scalability, and innovation. This paper investigates the potential of LLMs in automating Computer-Aided Design (CAD) workflows, by integrating FreeCAD with LLM as CAD design tool. Traditional CAD processes are often complex and require specialized sketching skills, posing challenges for rapid prototyping and generative design. We propose a framework where LLMs generate initial CAD scripts from natural language descriptions, which are then executed and refined iteratively based on error feedback. Through a series of experiments with increasing complexity, we assess the effectiveness of this approach. Our findings reveal that LLMs perform well for simple to moderately complex designs but struggle with highly constrained models, necessitating multiple refinements. The study highlights the need for improved memory retrieval, adaptive prompt engineering, and hybrid AI techniques to enhance script robustness. Future directions include integrating cloud-based execution and exploring advanced LLM capabilities to further streamline CAD automation. This work underscores the transformative potential of LLMs in design workflows while identifying critical areas for future development.

Web-enabled LLMs frequently answer queries without crediting the web pages they consume, creating an "attribution gap" - the difference between relevant URLs read and those actually cited. Drawing on approximately 14,000 real-world LMArena conversation logs with search-enabled LLM systems, we document three exploitation patterns: 1) No Search: 34% of Google Gemini and 24% of OpenAI GPT-4o responses are generated without explicitly fetching any online content; 2) No citation: Gemini provides no clickable citation source in 92% of answers; 3) High-volume, low-credit: Perplexity's Sonar visits approximately 10 relevant pages per query but cites only three to four. A negative binomial hurdle model shows that the average query answered by Gemini or Sonar leaves about 3 relevant websites uncited, whereas GPT-4o's tiny uncited gap is best explained by its selective log disclosures rather than by better attribution. Citation efficiency - extra citations provided per additional relevant web page visited - varies widely across models, from 0.19 to 0.45 on identical queries, underscoring that retrieval design, not technical limits, shapes ecosystem impact. We recommend a transparent LLM search architecture based on standardized telemetry and full disclosure of search traces and citation logs.