Graph Neural Networks (GNNs) (Kipf & Welling, 2016; Velickovic et al., 2017; Hamilton Graph Neural Networks (GNNs) have achieved et al., 2017), widely recognized as representative methodologies notable success in tasks such as social and transportation in graph-based machine learning, are capable of networks. However, recent studies have deriving high-quality representations from graph data. However, highlighted the vulnerability of GNNs to backdoor despite the remarkable performance of GNNs across attacks, raising significant concerns about various tasks, recent studies (Xi et al., 2021; Zhang et al., their reliability in real-world applications. Despite 2021; Dai et al., 2023; Zhang et al., 2024a) have revealed initial efforts to defend against specific graph that they are vulnerable to backdoor attacks. Backdoor attacks backdoor attacks, existing defense methods face on GNNs typically involve generating and attaching two main challenges: either the inability to establish backdoor triggers to a selected set of target nodes, which are a clear distinction between triggers and subsequently assigned to a specific target class. These triggers, clean nodes, resulting in the removal of many often represented as nodes or subgraphs, can be either clean nodes, or the failure to eliminate the impact predefined or dynamically created using a trigger generator. of triggers, making it challenging to restore the During training on a dataset contaminated with these triggers, target nodes to their pre-attack state. Through empirical due to the graph message-passing paradigm, the GNN analysis of various existing graph backdoor model learns to associate the presence of the trigger with attacks, we observe that the triggers generated by the specific target class. Consequently, during inference, the these methods exhibit over-similarity in both features backdoored model misclassifies test nodes containing the and structure. Based on this observation, we trigger into the target class while maintaining high predictive propose a novel graph backdoor defense method accuracy for clean nodes without triggers.

Understanding time series data is crucial for multiple real-world applications. While large language models (LLMs) show promise in time series tasks, current approaches often rely on numerical data alone, overlooking the multimodal nature of time-dependent information, such as textual descriptions, visual data, and audio signals. Moreover, these methods underutilize LLMs' reasoning capabilities, limiting the analysis to surface-level interpretations instead of deeper temporal and multimodal reasoning. In this position paper, we argue that multimodal LLMs (MLLMs) can enable more powerful and flexible reasoning for time series analysis, enhancing decision-making and real-world applications. We call on researchers and practitioners to leverage this potential by developing strategies that prioritize trust, interpretability, and robust reasoning in MLLMs. Lastly, we highlight key research directions, including novel reasoning paradigms, architectural innovations, and domain-specific applications, to advance time series reasoning with MLLMs.

Multi-label learning (MLL) has gained attention for its ability to represent real-world data. Label Distribution Learning (LDL), an extension of MLL to learning from label distributions, faces challenges in collecting accurate label distributions. To address the issue of biased annotations, based on the low-rank assumption, existing works recover true distributions from biased observations by exploring the label correlations. However, recent evidence shows that the label distribution tends to be full-rank, and naive apply of low-rank approximation on biased observation leads to inaccurate recovery and performance degradation. In this paper, we address the LDL with biased annotations problem from a novel perspective, where we first degenerate the soft label distribution into a hard multi-hot label and then recover the true label information for each instance. This idea stems from an insight that assigning hard multi-hot labels is often easier than assigning a soft label distribution, and it shows stronger immunity to noise disturbances, leading to smaller label bias. Moreover, assuming that the multi-label space for predicting label distributions is low-rank offers a more reasonable approach to capturing label correlations. Theoretical analysis and experiments confirm the effectiveness and robustness of our method on real-world datasets.

In this work, we introduce a novel framework for privately optimizing objectives that rely on Wasserstein distances between data-dependent empirical measures. Our main theoretical contribution is, based on an explicit formulation of the Wasserstein gradient in a fully discrete setting, a control on the sensitivity of this gradient to individual data points, allowing strong privacy guarantees at minimal utility cost. Building on these insights, we develop a deep learning approach that incorporates gradient and activations clipping, originally designed for DP training of problems with a finite-sum structure. We further demonstrate that privacy accounting methods extend to Wasserstein-based objectives, facilitating large-scale private training. Empirical results confirm that our framework effectively balances accuracy and privacy, offering a theoretically sound solution for privacy-preserving machine learning tasks relying on optimal transport distances such as Wasserstein distance or sliced-Wasserstein distance.

Human label variation (HLV) challenges the standard assumption that an example has a single ground truth, instead embracing the natural variation in human labelling to train and evaluate models. While various training methods and metrics for HLV have been proposed, there has been no systematic meta-evaluation of HLV evaluation metrics, contributing to the lack of clarity in the best HLV training method. We propose new evaluation metrics and training methods and empirically meta-evaluate HLV evaluation metrics. We find that training on either disaggregated annotations or soft labels often performs best across metrics, and that our proposed soft metric correlates best with human preference.

Detecting hallucinations in Large Language Models (LLMs) remains a critical challenge for their reliable deployment in real-world applications. To address this, we introduce SelfCheckAgent, a novel framework integrating three different agents: the Symbolic Agent, the Specialized Detection Agent, and the Contextual Consistency Agent. These agents provide a robust multi-dimensional approach to hallucination detection. Notable results include the Contextual Consistency Agent leveraging Llama 3.1 with Chain-of-Thought (CoT) to achieve outstanding performance on the WikiBio dataset, with NonFactual hallucination detection scoring 93.64%, Factual 70.26%, and Ranking 78.48% respectively. On the AIME dataset, GPT-4o with CoT excels in NonFactual detection with 94.89% but reveals trade-offs in Factual with 30.58% and Ranking with 30.68%, underscoring the complexity of hallucination detection in the complex mathematical domains. The framework also incorporates a triangulation strategy, which increases the strengths of the SelfCheckAgent, yielding significant improvements in real-world hallucination identification. The comparative analysis demonstrates SelfCheckAgent's applicability across diverse domains, positioning it as a crucial advancement for trustworthy LLMs. These findings highlight the potentiality of consistency-driven methodologies in detecting hallucinations in LLMs.

Contrastive Language-Image Pre-training (CLIP) has become the standard for cross-modal image-text representation learning. Improving CLIP typically requires additional data and retraining with new loss functions, but these demands raise resource and time costs, limiting practical use. In this work, we introduce HELIP, a cost-effective strategy that improves CLIP models by exploiting challenging text-image pairs within existing datasets in continuous training. This eliminates the need for additional data or extensive retraining. Moreover, HELIP integrates effortlessly into current training pipelines with minimal code modifications, allowing for quick and seamless implementation. On comprehensive benchmarks, HELIP consistently boosts existing models. In particular, within just two epochs of training, it improves zero-shot classification accuracy on ImageNet for SLIP models pre-trained on CC3M, CC12M, and YFCC15M datasets by 3.05%, 4.47%, and 10.1% , respectively. In addition, on fine-grained classification datasets, HELIP improves the zero-shot performance of CLIP and SLIP by an average of 8.4% and 18.6%, and their linear probe performance by an average of 9.5% and 3.0%. The code is publicly available at: https://github.com/haonan3/HELIP-NACCL-2025.git.

Since the explosion in popularity of ChatGPT, large language models (LLMs) have continued to impact our everyday lives. Equipped with external tools that are designed for a specific purpose (e.g., for flight booking or an alarm clock), LLM agents exercise an increasing capability to assist humans in their daily work. Although LLM agents have shown a promising blueprint as daily assistants, there is a limited understanding of how they can provide daily assistance based on planning and sequential decision making capabilities. We draw inspiration from recent work that has highlighted the value of 'LLM-modulo' setups in conjunction with humans-in-the-loop for planning tasks. We conducted an empirical study (N = 248) of LLM agents as daily assistants in six commonly occurring tasks with different levels of risk typically associated with them (e.g., flight ticket booking and credit card payments). To ensure user agency and control over the LLM agent, we adopted LLM agents in a plan-then-execute manner, wherein the agents conducted step-wise planning and step-by-step execution in a simulation environment. We analyzed how user involvement at each stage affects their trust and collaborative team performance. Our findings demonstrate that LLM agents can be a double-edged sword -- (1) they can work well when a high-quality plan and necessary user involvement in execution are available, and (2) users can easily mistrust the LLM agents with plans that seem plausible. We synthesized key insights for using LLM agents as daily assistants to calibrate user trust and achieve better overall task outcomes. Our work has important implications for the future design of daily assistants and human-AI collaboration with LLM agents.

Accurate sequence-to-sequence (seq2seq) alignment is critical for applications like medical speech analysis and language learning tools relying on automatic speech recognition (ASR). State-of-the-art end-to-end (E2E) ASR systems, such as the Connectionist Temporal Classification (CTC) and transducer-based models, suffer from peaky behavior and alignment inaccuracies. In this paper, we propose a novel differentiable alignment framework based on one-dimensional optimal transport, enabling the model to learn a single alignment and perform ASR in an E2E manner. We introduce a pseudo-metric, called Sequence Optimal Transport Distance (SOTD), over the sequence space and discuss its theoretical properties. Based on the SOTD, we propose Optimal Temporal Transport Classification (OTTC) loss for ASR and contrast its behavior with CTC. Experimental results on the TIMIT, AMI, and LibriSpeech datasets show that our method considerably improves alignment performance, though with a trade-off in ASR performance when compared to CTC. We believe this work opens new avenues for seq2seq alignment research, providing a solid foundation for further exploration and development within the community.

The introduction of robots into everyday scenarios necessitates algorithms capable of monitoring the execution of tasks. In this paper, we propose ConditionNET, an approach for learning the preconditions and effects of actions in a fully data-driven manner. We develop an efficient vision-language model and introduce additional optimization objectives during training to optimize for consistent feature representations. ConditionNET explicitly models the dependencies between actions, preconditions, and effects, leading to improved performance. We evaluate our model on two robotic datasets, one of which we collected for this paper, containing 406 successful and 138 failed teleoperated demonstrations of a Franka Emika Panda robot performing tasks like pouring and cleaning the counter. We show in our experiments that ConditionNET outperforms all baselines on both anomaly detection and phase prediction tasks. Furthermore, we implement an action monitoring system on a real robot to demonstrate the practical applicability of the learned preconditions and effects. Our results highlight the potential of ConditionNET for enhancing the reliability and adaptability of robots in real-world environments. The data is available on the project website: https://dsliwowski1.github.io/ConditionNET_page.