Visual questions are often ambiguous: the same image-question pair may admit multiple valid answers depending on which region is referenced.However, current Visual Question Answering (VQA) systems typically collapse this ambiguity, committing to a single interpretation during decoding and evaluation.In this work, we study visual question ambiguity from a grounded, region-centric perspective.We operationalize ambiguity as the existence of multiple distinct answer-supporting regions in an image, each independently yielding a valid answer.This formulation makes ambiguity observable without requiring exhaustive multi-answer annotations.Based on this definition, we conduct a systematic empirical study of state-of-the-art Visual Large Language Models (VLLMs).We find that, under default decoding, VLLMs consistently under-report ambiguity-even when multiple valid visual groundings are present.Importantly, probing model hidden states reveals that ambiguity-related signals are already encoded in their internal representations, despite not being reliably expressed in outputs.Finally, we show that selectively activating multi-focus answering based on these signals can recover additional valid answers while avoiding excessive hallucination.Together, our results suggest that ambiguity in VQA is not merely an annotation artifact or capability limitation, but a property that VLLMs internally recognize yet often fail to surface under standard decoding assumptions.

Multi-access point coordination (MAPC) is a key technology for enhancing throughput in next-generation Wi-Fi within dense overlapping basic service sets. However, existing MAPC protocols rely on static, protocol-defined rules, which limits their ability to adapt to dynamic network conditions such as varying interference levels and topologies. To address this limitation, we propose a novel Agentic AI Wi-Fi framework where each access point, modeled as an autonomous large language model agent, collaboratively reasons about the network state and negotiates adaptive coordination strategies in real time. This dynamic collaboration is achieved through a cognitive workflow that enables the agents to engage in natural language dialogue, leveraging integrated memory, reflection, and tool use to ground their decisions in past experience and environmental feedback. Comprehensive simulation results demonstrate that our agentic framework successfully learns to adapt to diverse and dynamic network environments, significantly outperforming the state-of-the-art spatial reuse baseline and validating its potential as a robust and intelligent solution for future wireless networks.

Clarification Question Generation (abbr., CQG) is crucial for ambiguous question answering. It produces the structured "clarification question" to reveal the intention and possible answers. Currently, the existing CQG approach is grounded on a pipeline mode, i.e., predicting possible answers first, and further performing CQG accordingly. This approach is applicable and obtains promising performance. However, it suffers from an unavoidable bottleneck that the distinctions among the answers are difficult to perceive, while such distinctions reveal significantly different intentions of questions. Without the ability of distinction perception and differentiation, the generator easily falls into the hallucination caused by distracting intentions. To address the issues, we construct an end-to-end CQG model using multitask learning. In particular, we propose an Answer-oriented Distinction Perception (ADP) approach to enhance the multi-task learning process. Specifically, ADP conducts comparison between a pair of possible answers, and instructs the Large Language Model (LLM) to summarize their distinction. We integrate ADP into the multi-task learning framework, progressively coupling it with possible answer generation and CQG to form different auxiliary tasks. The goal is to obtain the generalized distinction-aware CQG model. In our experiments, we use LLaMA3 as the backbone of CQG, and fine-tune it by multi-task learning. We leverage ChatGPT to produce the distinction descriptions among possible answers, and use them as observable evidence to fine-tune LLaMA3 for ADP. We evaluate our CQG model on the benchmark dataset CAmbigNQ. The test result shows that our ADP-based end-to-end CQG obtains substantial improvements compared to the pipeline CQG model. In addition, we apply our CQG model to the downstream ambiguous question answering task, and achieve an F1-score of 45.1% with an improvement of 5.9% at best (4.1% at worst).

A cryptographic implementation produces very similar power leakages when fed with the same input. Side-channel collision attacks exploit these similarities to establish the relationship between sub-keys and improve the efficiency of key recovery. Benefiting from independence of leakage model, they play an important role in non-profiled setting. However, performance of existing approaches against single collision value is still sub-optimal and optimization is promising. Motivated by this, we first theoretically analyze the mathematical dependency between the number of collisions and the number of encryptions, and propose an efficient side-channel attack named Collision-Paired Correlation Attack (CPCA) to guarantee that the side with fewer samples in a collision is completely paired in low noise scenario. This allows overcoming the inefficient utilization of information in existing works. Moreover, to further employ underlying informativeness, we maximize collision pairs as many as possible. This optimization significantly improves performance of CPCA and thereby extends it to large noise scenarios. Finally, to achieve moderate computational complexity, two equivalent variants of CPCA are investigated to address the potential problem of limited computing resources. Our further theoretical study illustrates that CPCA provides the upper security bound of Correlation-Enhanced Collision Attack (CECA), and experimental results fully verify its superiority.

Side-channel attacks (SCAs) seriously threaten the security of cryptographic hardwares and embedded systems, especially following the introduction of deep learning techniques, with their powerful feature extraction capability that enables attackers to analyze the key information more efficiently. However, deep learning models in side-channel attacks also face with the problems of excessive model complexity and long training time. In this paper, we introduce Broad Learning Systems (BLS) to power side-channel attacks (SCAs) and then construct an efficient model of broad learning for power SCAs from the core of BLS. Then we optimize the model by making full use of the excellent features of incremental learning and feature extraction of BLS. Finally, we verify the effectiveness of the optimization model in diverse side-channel attack scenarios, achieving stable accuracy levels above 85% while significantly reducing time consumption compared to other models. This fully illustrates the superiority of our scheme.

We propose a novel, cost-effective soft sensor capable of detecting contact force, multiple touch points, and reflecting sensor interaction in real-time with a 3D virtual surface representation. Our fabrication process has been optimized for cost efficiency through careful material selection, utilization of automated machinery, and low-cost hardware. The sensor can be easily replicated without the need for complex laboratory equipment. The sensor employs trained neural network models for real-time signal translation into localization, force measurement, and deformation mapping. We have also developed an efficient data collection system that captures accurate 2D localization, force measurement, and 3D surface data to generate a high-quality pre-validated data set. This data set is filtered using prior knowledge before being fed to two neural network models. Our interactive prototype demonstrates the stability and accuracy of the low-cost soft sensor, delivering reliable results in both single-point and multi-point contact scenarios.

Conversational Question Answering (CQA) aims to provide natural language answers to users in information-seeking dialogues.Existing CQA benchmarks often evaluate models using pre-collected human-human conversations.However, replacing the model-predicted dialogue history with ground truth compromises the naturalness and sustainability of CQA evaluation.While previous studies proposed using predicted history and rewriting techniques to address unresolved coreferences and incoherencies, this approach renders the question self-contained from the conversation.In this paper, we propose a novel automatic evaluation approach, interview evaluation.Specifically, ChatGPT acts as the interviewer (Q agent) with a set of carefully designed prompts, and the CQA model under test serves as the interviewee (A agent).During the interview evaluation, questions are dynamically generated by the Q agent to guide the A agent in predicting the correct answer through an interactive process.We evaluated four different models on QuAC and two models on CoQA in our experiments.The experiment results demonstrate that our interview evaluation has advantages over previous CQA evaluation approaches, particularly in terms of naturalness and coherence.The source code is made publicly available.

We tackle Multi-party Dialogue Reading Comprehension (abbr., MDRC). MDRC stands for an extractive reading comprehension task grounded on a batch of dialogues among multiple interlocutors. It is challenging due to the requirement of understanding cross-utterance contexts and relationships in a multi-turn multi-party conversation. Previous studies have made great efforts on the utterance profiling of a single interlocutor and graph-based interaction modeling. The corresponding solutions contribute to the answer-oriented reasoning on a series of well-organized and thread-aware conversational contexts. However, the current MDRC models still suffer from two bottlenecks. On the one hand, a pronoun like “it” most probably produces multi-skip reasoning throughout the utterances of different interlocutors. On the other hand, an MDRC encoder is potentially puzzled by fuzzy features, i.e., the mixture of inner linguistic features in utterances and external interactive features among utterances. To overcome the bottlenecks, we propose a coreference-aware attention modeling method to strengthen the reasoning ability. In addition, we construct a two-channel encoding network. It separately encodes utterance profiles and interactive relationships, so as to relieve the confusion among heterogeneous features. We experiment on the benchmark corpora Molweni and FriendsQA. Experimental results demonstrate that our approach yields substantial improvements on both corpora, compared to the fine-tuned BERT and ELECTRA baselines. The maximum performance gain is about 2.5%$F\mathbf{1}-\mathbf{score}$. Besides, our MDRC models outperform the state-of-the-art in most cases.

Generative commonsense question answering (GenCQA) is a task of automatically generating a list of answers given a question. The answer list is required to cover all reasonable answers. This presents the considerable challenges of producing diverse answers and ranking them properly. Incorporating a variety of closely-related background knowledge into the encoding of questions enables the generation of different answers. Meanwhile, learning to distinguish positive answers from negative ones potentially enhances the probabilistic estimation of plausibility, and accordingly, the plausibility-based ranking. Therefore, we propose a Knowledge Enhancement and Plausibility Ranking (KEPR) approach grounded on the Generate-Then-Rank pipeline architecture. Specifically, we expand questions in terms of Wiktionary commonsense knowledge of keywords, and reformulate them with normalized patterns. Dense passage retrieval is utilized for capturing relevant knowledge, and different PLM-based (BART, GPT2 and T5) networks are used for generating answers. On the other hand, we develop an ELECTRA-based answer ranking model, where logistic regression is conducted during training, with the aim of approximating different levels of plausibility in a polar classification scenario. Extensive experiments on the benchmark ProtoQA show that KEPR obtains substantial improvements, compared to the strong baselines. Within the experimental models, the T5-based GenCQA with KEPR obtains the best performance, which is up to 60.91% at the primary canonical metric Inc@3. It outperforms the existing GenCQA models on the current leaderboard of ProtoQA.

Leveraging external knowledge to enhance the reasoning ability is crucial for commonsense question answering. However, the existing knowledge bases heavily rely on manual annotation which unavoidably causes deficiency in coverage of world-wide commonsense knowledge. Accordingly, the knowledge bases fail to be flexible enough to support the reasoning over diverse questions. Recently, large-scale language models (LLMs) have dramatically improved the intelligence in capturing and leveraging knowledge, which opens up a new way to address the issue of eliciting knowledge from language models. We propose a Unified Facts Obtaining (UFO) approach. UFO turns LLMs into knowledge sources and produces relevant facts (knowledge statements) for the given question. We first develop a unified prompt consisting of demonstrations that cover different aspects of commonsense and different question styles. On this basis, we instruct the LLMs to generate question-related supporting facts for various commonsense questions via prompting. After facts generation, we apply a dense retrieval-based fact selection strategy to choose the best-matched fact. This kind of facts will be fed into the answer inference model along with the question. Notably, due to the design of unified prompts, UFO can support reasoning in various commonsense aspects (including general commonsense, scientific commonsense, and social commonsense). Extensive experiments on CommonsenseQA 2.0, OpenBookQA, QASC, and Social IQA benchmarks show that UFO significantly improves the performance of the inference model and outperforms manually constructed knowledge sources.

We propose a novel evaluation method for Question Generation (QG) task. It is designed to verify the quality of the generated questions in terms of different references, including not only the manually-written questions (i.e., ground truth) but also their variants. Back translation is utilized to obtain the variants, and accordingly, they generally appear as paraphrases of the ground-truth examples. In particular, an Asymmetrical Twin Gain (ATG) is proposed for binary-perspective evaluation using the existing metrics, such as BLEU and ROUGE-L, respectively. It enables both the metrics to be observed from two perspectives, including the consistency between QG results and ground-truth examples, as well as that of variants. The experiments on the publicly-available benchmark SQuAD demonstrate the reliability of ATG. More importantly, ATG is proven effective for indicating the stable QG performance. It is noteworthy that the proposed binary-perspective evaluation is explored for assisting the conventional evaluation methods, instead of replacing them. The contribute can be identified as the additional insight into the robustness of QG when some slightly-different references (e.g., paraphrases) are offered for evaluation. All the models and source codes in the experiments will be made publicly available to support reproducible research.

Dialogue systems provide a very efficient way for humans to interact with computer systems to access various resources and services. The evaluation of a dialogue system can provide valuable feedback for improving the system, but it is a challenging task, so attracts lots of attention from researchers. In this paper, we survey some essential criteria and widely used methods for evaluating dialogue systems, focusing on the latest research progress on this topic. Notably, we discuss machine learning based evaluation method and deep learning based ones. We also compare their advantages and disadvantages. Besides, by analysing the difficulties and challenges that the researchers face in evaluating dialogue systems, we prospect the development tendency of the research on evaluating dialogue systems.