The paper investigates how encoder-decoder models in ASR and NMT can generate fluent text even when the input contains no recoverable message, a phenomenon known as message-free hallucination. By auditing the models’ reserved null tokens and manipulating their scores, the authors show that a higher null-token score can suppress fabrication but may also delete valid content or shorten translations. The study highlights that the null token can serve as a diagnostic tool for hallucination and suggests evaluating abstention methods by considering both suppression and deletion costs.
By Kirill Borodin, Vasiliy Kudryavtsev, Ivan Viakhirev
arXiv:2608. 16747v1 Announce Type: cross Abstract: Many areas of AI research, such as language model interpretability and chain of thought faithfulness, seek to explain model behaviors.
By Adam Karvonen, Euan Ong, Subhash Kantamneni, Samuel Marks
arXiv:2608. 15715v1 Announce Type: cross Abstract: Quantum feedback control requires acting on noisy continuous measurement records without direct access to the underlying quantum state.
By Priyanshi Singh, Krishna Bhatia
arXiv:2608. 16834v1 Announce Type: cross Abstract: We demonstrate that AI models are broadly susceptible to a phenomenon we call model hypnosis, in which individually weak and seemingly irrelevant cues in the prompt can be systematically combined to strongly control model behavior.
By Enric Boix-Adsera, Benedict Tessler
arXiv:2508. 09105v3 Announce Type: replace Abstract: Retrieval-Augmented Generation (RAG) and its Multimodal Retrieval-Augmented Generation (MRAG) significantly improve the knowledge coverage and contextual understanding of Large Language Models (LLMs) by introducing external knowledge sources.
By Shixuan Sun, Siyuan Liang, Jianjie Huang, Jingzhi Li, Xiaochun Cao
arXiv:2608. 15770v1 Announce Type: new Abstract: Designing effective trading strategies using reinforcement learning remains challenging due to delayed and noisy rewards, poor exploration, and the difficulty of enforcing explicit risk constraints.
By Arishi Orra, Himanshu Choudhary, Manoj Thakur
arXiv:2601. 03506v2 Announce Type: replace-cross Abstract: Recent large reasoning models (LRMs) have achieved strong performance on complex reasoning tasks by generating a long chain-of-thought (Long-CoT).
By Zhaofeng Zhong, Wei Yuan, Tong Chen, Liang Qu, Xiangyu Zhao, Quoc Viet Hung Nguyen, Hongzhi Yin
arXiv:2608. 15762v1 Announce Type: cross Abstract: Container-granularity scheduling leaves abundant short-lived idle slices within containers unexploited.
By Weinan Liu, Zeyuan Ding, Dian Ding, Chengcheng Wan, Lu Tang, Guangtao Xue, Jiwu Shu, Yiming Zhang
arXiv:2608. 15365v1 Announce Type: new Abstract: Regret minimization (RM) and best-arm identification (BAI) are two fundamental objectives in multi-armed bandits.
By Jingxin Zhan, Yuze Han, Zhihua Zhang
arXiv:2608. 16390v1 Announce Type: cross Abstract: PDF corpora advertise their size in tokens but compute every rate they publish (coverage, OCR routing, re-fetch recovery, language mix) per document, and none decomposes its token total.
By Luca Foppiano
arXiv:2510. 04927v2 Announce Type: replace-cross Abstract: Automatic modulation classification (AMC) is a core enabler of cognitive wireless systems, providing spectrum awareness and supporting adaptive communication at the network edge.
By Usman Akram, Yiyue Chen, Haris Vikalo
arXiv:2608. 16407v1 Announce Type: cross Abstract: Point-of-interest (POI) recommendation models based on graph neural networks achieve strong performance by propagating collaborative signals over user-item interactions, yet they struggle with the cold-start problem, where items with few or no interactions are not represented.
By Burak Tamer, Wolfram H\"opken, Zehui Wang
Agent Skills can specify procedural and resource obligations for tool use, and language models instantiate them as concrete programs. However, when models turn this guidance into code for existing too...
Humanoid robots hold great promise as general-purpose agents in human-centered environments, yet generalist vision-language-action (VLA) foundation models are not readily applicable to humanoid whole-body loco-manipulation. The high dimensionality and interdependence of humanoid motions make it challenging for conventional single-stage VLA architectures to coordinate locomotion, waist posture, and dual-arm manipulation effectively.
Large vision-language models can recognize the objects and attributes in a crowded scene yet assign an attribute to the wrong same-class instance. Generic visual-question-answering accuracy marks the...
Unified image restoration (UIR) aims to recover high-quality (HQ) content from low-quality (LQ) images with different degradations using a single model. Most recent methods adapt large pretrained text-to-image (T2I) latent diffusion models for their strong capacity and generative priors.
Empathetic social robots should respond not only to what users say, but also to how their emotions dynamically evolve during interaction. However, existing empathetic dialogue systems are often text-c...
With the rapid advancement of large language models, brain-language decoding has achieved remarkable progress. However, it remains unclear whether decoded content genuinely reflects neural representat...
The impressive visual quality and ubiquity of AI-generated images call for reliable and robust detection methods. Reconstruction-based detectors have emerged as a promising direction for transparent and training-free identification of synthetic images.
Automated detection of errors in clinical documentation is a promising application of large language models (LLMs), yet decisions to deploy such models rest on benchmarks that evaluate each clinical note in isolation. Error-detection benchmarks are typically constructed by injecting errors into notes, such that each erroneous note has a natural counterpart.