Search agents, which integrate language models (LMs) with web search, are becoming crucial for answering complex user queries. Constructing training datasets fo...
Can a large language model (LLM) improve at code generation using only its own raw outputs, without a verifier, a teacher model, or reinforcement learning? We a...
This study investigates the ability of multimodal Large Language Models (LLMs) to identify and interpret misleading visualizations, and recognize these observat...
A core limitation of standard softmax attention is that it does not define a notion of absolute query--key relevance: attention weights are obtained by redistri...
While test-time scaling has enabled large language models to solve highly difficult tasks, state-of-the-art results come at exorbitant compute costs. These inef...
Using roughly 48 execution-verified HumanEval training solutions, tuning a single initial state matrix per recurrent layer, with zero inference overhead, outper...
We present Brainstacks, a modular architecture for continual multi-domain fine-tuning of large language models that packages domain expertise as frozen adapter ...
Multi-LLM revision pipelines, in which a second model reviews and improves a draft produced by a first, are widely assumed to derive their gains from genuine er...
This study investigates the use of NeuralUCB for cost-aware large language model (LLM) routing. Existing routing approaches can be broadly grouped into supervis...
Human talkers often address listeners with language-comprehension challenges, such as hard-of-hearing or non-native adults, by globally slowing down their speec...
Verifiable claim detection asks whether a claim expresses a factual statement that can, in principle, be assessed against external evidence. As an early filteri...
Mechanistic interpretability (MI) is an emerging framework for interpreting neural networks. Given a task and model, MI aims to discover a succinct algorithmic ...
Analogical reasoning is a key driver of human generalization in problem-solving and argumentation. Yet, analogies between narrative structures remain challengin...
The proliferation of AI-powered search engines has shifted information discovery from traditional link-based retrieval to direct answer generation with selectiv...
Effective collaboration requires teams to manage complex cognitive and emotional states through Socially Shared Regulation of Learning (SSRL). Physiological syn...
This paper investigates sentence-level text reuse in multilingual journalism, analyzing where reused content occurs within articles. We present a weakly supervi...
Automated radiology report summarization aims to distill verbose findings into concise clinical impressions, but existing multimodal models often struggle with ...
FLEURS offers n-way parallel speech for 100+ languages, but Northern Kurdish is not one of them, which limits benchmarking for automatic speech recognition and ...
NVFP4 has grown increasingly popular as a 4-bit format for quantizing large language models due to its hardware support and its ability to retain useful informa...
We introduce ParaSpeechCLAP, a dual-encoder contrastive model that maps speech and text style captions into a common embedding space, supporting a wide range of...
Vision-language models (VLMs) have shown impressive capabilities across diverse tasks, motivating efforts to leverage these models to supervise robot learning. ...
Epilepsy and psychogenic non-epileptic seizures often present with similar seizure-like manifestations but require fundamentally different management strategies...
Psychological scale development has traditionally required extensive expert involvement, iterative revision, and large-scale pilot testing before psychometric e...
Multimodal Large Language Models (MLLMs) achieve stronger visual understanding by scaling input fidelity, yet the resulting visual token growth makes jointly su...
Reflective writing is known to support the development of students' metacognitive skills, yet learners often struggle to engage in deep reflection, limiting lea...
Every 4 years, the PISA test is administered by the OECD to test the knowledge of teenage students worldwide and allow for comparisons of educational systems. H...
Transformer-based language models achieve strong performance across NLP tasks, but their quadratic parameter scaling with hidden dimension makes deployment on r...
Agentic knowledge graph question answering (KGQA) requires an agent to iteratively interact with knowledge graphs (KGs), posing challenges in both training data...
!Cover image for Understanding Attention Mechanisms – Part 3: From Cosine Similarity to Dot Producthttps://media2.dev.to/dynamic/image/width=1000,height=420,fit...
Large language model (LLM)-based coding agents achieve impressive results on controlled benchmarks yet routinely produce pull requests that real maintainers rej...
Weight tying, i.e. sharing parameters between input and output embedding matrices, is common practice in language model design, yet its impact on the learned em...
We introduce PerceptionComp, a manually annotated benchmark for complex, long-horizon, perception-centric video reasoning. PerceptionComp is designed so that no...
This paper investigates the relationship between utterance sentiment and language choice in English-Tamil code-switched text, using methods from machine learnin...
Large Language Models (LLMs) deliver strong performance but incur high inference cost in real-world services, especially under workloads with repeated or near-d...
Converting a pretrained Transformer into a more efficient hybrid model through distillation offers a promising approach to reducing inference costs. However, ac...
Background: The identification of optimal signal detection methods is hindered by the lack of reliable reference datasets. Existing datasets do not capture when...
How does the extent to which a model is open or closed impact the scientific inferences that can be drawn from research that involves it? In this paper, we anal...
As Large Language Models (LLMs) expand across multilingual domains, evaluating their performance in under-represented languages becomes increasingly important. ...
Despite recent advances, efficient and robust turn-taking detection remains a significant challenge in industrial-grade Voice AI agent deployments. Many existin...
We present H-Node Adversarial Noise Cancellation (H-Node ANC), a mechanistic framework that identifies, exploits, and defends hallucination representations in t...
The knowledge base in a retrieval-augmented generation (RAG) system is typically assembled once and never revised, even though the facts a query requires are of...
Agent performance increasingly depends on harness engineering, yet harness design is usually buried in controller code and runtime-specific conventions, making ...
Block-diffusion language models offer a promising path toward faster-than-autoregressive generation by combining block-wise autoregressive decoding with within-...
As large language models (LLMs) continue to advance, improving them solely through human supervision is becoming increasingly costly and limited in scalability....
Automated systems have been widely adopted across the educational testing industry for open-response assessment and essay scoring. These systems commonly achiev...
Accurate parsing of citations is necessary for machine-readable scholarly infrastructure. But, despite sustained interest in this problem, existing evaluation t...
Through an analysis of arXiv papers, we report several shifts in word usage that are likely driven by large language models (LLMs) but have not previously recei...
Large language model (LLM)-based persona agents are rapidly being adopted as scalable proxies for human participants across diverse domains. Yet there is no sys...
