Aligned language models routinely misreport under non-evidential incentive pressure: they agree with a confident user or overstate certainty even when their internal belief is unchanged. We cast this as a failure of internal incentive-compatibility (IC) and present a method for learning and certifying counterfactual report mediators that hold a model's reports to a causal contract: invariant to forbidden influences (pressure, prestige, restyling) and responsive to licensed ones (genuine evidence).
Quantum circuit optimization for fault-tolerant computing requires exact functional equivalence while minimizing expensive non-Clifford resources such as T gates. We study this problem using a compact 44.
The rapid advancement of synthetic speech generation methods has made audio deepfake detection a critical challenge in multimedia forensics. While recent approaches achieve high detection accuracy, they typically rely on black-box architectures that offer limited interpretability and high computational complexity.
Speculative decoding accelerates autoregressive language model inference by using a cheap drafter to propose multiple future tokens and a target model to verify them. A common design goal is therefore to improve draft quality while reducing auxiliary parameters and systems overhead.
Large-scale Vision-Language Models have demonstrated impressive transfer learning capabilities across a wide range of tasks. For few-shot classification, we observe that VLMs exhibit a notable ability to filter candidate categories and thus achieve high Top-K accuracy.
arXiv:2607. 11843v1 Announce Type: cross Abstract: Quantum Neural Networks (QNNs) are a promising framework for quantum machine learning on near-term quantum devices, but their security risks remain insufficiently understood.
By Junrui Zhang, Zemin Chen, Lusi Li, Mohammad Ghasemigol, Daniel Takabi, Rui Ning
arXiv:2506. 21833v2 Announce Type: replace Abstract: Forward-mode automatic differentiation (FmAD) and zero-order (ZO) optimization are increasingly proposed as memory-efficient, backpropagation-free alternatives for large language model (LLM) fine-tuning, yet their benefits are typically evaluated only against standard backpropagation (BP), omitting memory-efficient variants such as activation checkpointing.
By Kunjal Panchal, Sunav Choudhary, Yuriy Brun, Hui Guan
arXiv:2607. 10366v1 Announce Type: new Abstract: Offline-trained surrogates for Inertial Confinement Fusion (ICF) suffer a well-known failure mode that iterative optimizers drive inputs into out-of-distribution (OOD) regions where predictions become unreliable.
By Jiatong Zhao, Tengyue Zhang, Yuhan Wang, Fuyuan Wu, Junchi Yan
arXiv:2607. 09957v1 Announce Type: cross Abstract: This report studies on-device English-to-Traditional-Chinese subtitle translation for Taiwan under short inputs, short outputs, batch-size-one inference, low latency, and privacy constraints.
By Tsz-To Wong
arXiv:2601. 07155v3 Announce Type: replace-cross Abstract: Knowledge distillation (KD) is a widely adopted technique for transferring knowledge from large language models to smaller student models; however, conventional supervised KD often suffers from a distribution mismatch between training and inference.
By Ijun Jang, Jewon Yeom, Juan Yeo, Hyunggyu Lim, Taesup Kim
arXiv:2602. 17993v2 Announce Type: replace-cross Abstract: Complex problems, whether in math, logic, or planning, are solved by humans through a sequence of steps where the result of one step informs the next.
By Mohan Tang, Sidi Lu
arXiv:2604. 00878v2 Announce Type: replace-cross Abstract: Actor-level stance detection aims to determine an author expressed position toward specific geopolitical actors mentioned or implicated in a text.
By Abdullah Al Shafi, Md. Milon Islam, Sk. Imran Hossain, K. M. Azharul Hasan
arXiv:2607. 11119v1 Announce Type: cross Abstract: Robot manipulation is a complex task that requires visual understanding, physical reasoning, planning, and closed-loop control.
By Hengyuan Hu, Priya Sundaresan, Jensen Gao, Dorsa Sadigh
arXiv:2607. 11475v1 Announce Type: new Abstract: Safety alignment in large language models can be fragile under fine-tuning, as even benign task adaptation may increase harmful compliance.
By Aznaur Aliev, Carlos Hinojosa, Abdelrahman Eldesokey, Bang An, Bernard Ghanem, Yibo Yang
arXiv:2607. 10517v1 Announce Type: cross Abstract: Activation steering offers a lightweight alternative to fine-tuning for controlling large language models at inference time.
By Seyed Arshan Dalili, Ajay Narayanan Sridhar, Vijaykrishnan Narayanan, Mehrdad Mahdavi
arXiv:2607. 10630v1 Announce Type: cross Abstract: Robust motion planning in dense traffic requires autonomous vehicles to interact in rare and safety-critical scenarios that are underrepresented in naturalistic driving data.
By Tong Nie, Yuewen Mei, Junlin He, Yihong Tang, Jian Sun, Wei Ma
arXiv:2607. 10190v1 Announce Type: cross Abstract: Video-language models (VLMs) have achieved remarkable performance on video understanding and visual question answering, yet they remain unreliable in reasoning about physical plausibility, where understanding object interactions, causal dynamics, and fundamental physical principles is essential.
By Wenyuan Wang, Lianyu Hu, Hao Wang, Yang Liu
arXiv:2607. 10312v1 Announce Type: cross Abstract: The rapid proliferation of online polarization threatens social cohesion, necessitating robust automated detection systems that operate effectively across diverse linguistic contexts.
By Muhammad Abdullahi Said
arXiv:2607. 11839v1 Announce Type: cross Abstract: This paper presents a cascaded Low-Rank Adaptation (LoRA)-based multimodal fusion framework for action and activity recognition in healthcare-oriented training environments.
By Divya Mereddy, Jeevan Beedareddy
arXiv:2607. 11289v1 Announce Type: cross Abstract: Backpropagation is the computational engine of deep learning, yet its mathematical structure is typically treated as a procedural traversal of computational graphs.
By Ahmed Boughammoura