Search the full wire by company, model, lab, or keyword. Every story we have ever aggregated.
Humans are the bottleneck in building and improving AI. Both the models and the agents that wrap them are written, tuned, and corrected by people. The long-horizon goal of an AI that can figure out how to improve itself remains open. Two largely disjoint research lines attack…
# ok so i was working on this projectt and INSTEAD of just doing it i kept asking claude ai to verify all the requirments were met right like i would go "did you complete EVERYTHING" it would go "yes all done :))" and then i check myself and requirments 5 and 6 are just…
Disease forecasting models typically rely on a single data stream, making models brittle when histories are short or noisy. Recent top-performing models have shown that synthesizing multiple reporting systems for the same disease improves performance. Other recent work takes…
Modern Large Language Models (LLMs) are often criticized for producing repetitive and homogeneous text, despite possessing vast latent vocabularies. While previous research has focused on model knowledge and training data, we investigate the role of decoding mechanics in…
We propose Kan Extension Transformers (KETs) as a unifying categorical framework for a diverse group of Transformer implementations. The core claim is that a Transformer layer can be viewed as a weighted structured extension operator: standard attention is the…
Building state-of-the-art text-to-speech (TTS) systems typically demands millions of hours of proprietary data and complex multi-stage architectures, creating substantial barriers for resource-constrained research teams. In this report, we present PilotTTS, a lightweight…
Long chain-of-thought reasoning has made autoregressive decoding the dominant inference cost of modern large language models. Existing methods target either the input side (latent compression) or the output side (speculative decoding and multi-token prediction, MTP), but the…
Selecting which instances to label is a key challenge in low-label tabular learning. For recent Tabular Foundation Models such as TabPFN, context selection directly determines predictive performance. Supervised oracle experiments show that carefully chosen labeled context sets…
An effective method of teaching across disciplines is to provide examples of high-quality work. However, an example may be significantly different from a student's current work, making it challenging for them to emulate. An ideal learning demonstration is a counterfactual…
This position statement looks back on two decades of work on shallow embeddings of non-classical logics in classical higher-order logic (HOL), a line of research that expanded into a range of logic embeddings in HOL and inspired the LogiKEy logic-pluralistic knowledge…
Symbolic regression (SR) seeks closed-form mathematical expressions that fit observed data. Neural SR methods amortize the search by training an encoder to map observations directly to expressions in a single pass, but this amortized inference leaves a residual amortization gap…
Memory-augmented language agents are increasingly deployed in affective applications such as emotional support, where understanding and responding to users' latent emotional needs is critical. However, existing research often treats memory as a tool for factual retrieval…
Annotation quality is difficult to sustain when campaigns span weeks or months with small annotator pools. We present a Setswana sentiment dataset of 3,565 tweets annotated by three native-speaker annotators across eight batches and examine why inter-annotator agreement (IAA)…
Continuous and global detection of large methane emissions is a crucial step for global warming mitigation. Satellite observations, such as from S5P/TROPOMI, combined with plume detection algorithms, can play a key role in this effort. However, not all TROPOMI plume detections…
In modern RAG pipelines, query augmentation methods such as HyDE and query expansion are applied to every query, resulting in substantial LLM inference costs and increased end-to-end latency. The empirical justification for this overhead in real production traffic remains…
Collaborative analysis of decentralized confidential datasets is important, but direct sharing of original datasets is often restricted by privacy and institutional constraints. Data collaboration (DC) analysis transforms each dataset into privacy-preserving intermediate…
We adapt Microsoft's QuantumKatas -- a well-established quantum computing curriculum -- from Q# to Qiskit, the most widely-adopted quantum computing framework, and package it with an evaluation framework for systematic LLM assessment. The resulting benchmark comprises 350 tasks…
Recent advances in large language models (LLMs) have facilitated the widespread deployment of LLMs as interactive agents capable of reasoning, planning, and tool use. Despite strong performance on existing benchmarks, such agents often exhibit notable degradation when deployed…
Precision medicine depends on two fundamental capabilities: understanding disease at the genomic level and identifying treatments at the molecular level. ... Precision medicine depends on two fundamental capabilities: understanding disease at the genomic level and identifying…
Human Archive, a startup founded by Berkeley and Stanford researchers, is paying gig workers in India to wear camera-equipped caps and sensor devices to collect the real-world physical training data that AI and robotics labs are racing to acquire.
Wireless digital twins require repeated synchronization between a time-evolving physical scene and its digital counterpart under limited and time-varying communication resources. For perception-centric twins, pixel-domain transmission or uniformly protected bitstreams can be…
Scientific paper evaluation often involves not only assessing a manuscript itself, but also relating it to contemporaneous research and prior literature. However, existing LLM-based methods typically model these signals separately and lack a unified mechanism for propagating…
Animation elevates digital documents into immersive experiences, yet creating custom motion paths remains cumbersome, requiring designers to manually select presets, plot Bézier points, and configure timing properties. We introduce Generative Animations, a system that…
I know this topic is discussed here a lot but I SWEAR TO FUCKING GOD if I read another "That is real" OR "That is not nothing" OR "That is not X but Y" I am going to have a fucking aneurysm. Yes I have specifically forbidden it from telling me these phrases, yes I have…
Chart-to-data extraction with vision-language models (VLMs) is increasingly evaluated on benchmarks that show diminishing headroom (frontier VLMs exceed 89% on ChartQA) and with metrics that treat extracted points as unordered key-value pairs, ignoring the temporal structure of…
Distilling demonstration effects into hidden-space interventions offers a lightweight alternative to full finetuning. However, existing multimodal variants are mostly evaluated on short-form tasks, where outputs end after a few tokens. Extending these methods to long-form…
Recent advances in Large Audio-Language Models (LALMs) have made real-time, streaming spoken interaction increasingly practical. In this setting, reasoning quality and responsiveness are tightly coupled: delaying reasoning until the speech endpoint can improve answer quality…