However, pre-trained VLA policies still suffer from substantial performance degradation during downstream deployment. Although fine-tuning can mitigate this issue, its reliance on costly demonstration collection and intensive computation makes it impractical in real-world settings. In this work, we introduce VLA-Pilot, a plug-and-play inference-time policy steering method for zero-shot deployment of pre-trained VLA without any additional fine-tuning or data collection. We evaluate VLA-Pilot on six real-world downstream manipulation tasks across two distinct robotic embodiments, encompassing both in-distribution and out-of-distribution scenarios. Experimental results demonstrate that VLA-Pilot substantially boosts the success rates of off-the-shelf pre-trained VLA policies, enabling robust zero-shot generalization to diverse tasks and embodiments. Experimental videos and code are available at: https://rip4kobe.github.io/vla-pilot/. I. INTRODUCTION Recent advances in VLA models have substantially improved the generalization capabilities of robotic manipulation. By learning from large-scale demonstrations [1], these generative foundation policies enable robots to acquire a wide repertoire of skills. At inference time, they can perform diverse and contextually appropriate tasks by stochastically sampling actions from the learned skill distribution.

LLMs still struggle with hallucination, especially when confronted with symbolic triggers like modifiers, negation, numbers, exceptions, and named entities. Yet, we lack a clear understanding of where these symbolic hallucinations originate, making it crucial to systematically handle such triggers and localize the emergence of hallucination inside the model. While prior work explored localization using statistical techniques like LSC and activation variance analysis, these methods treat all tokens equally and overlook the role symbolic linguistic knowledge plays in triggering hallucinations. So far, no approach has investigated how symbolic elements specifically drive hallucination failures across model layers, nor has symbolic linguistic knowledge been used as the foundation for a localization framework. We propose the first symbolic localization framework that leverages symbolic linguistic and semantic knowledge to meaningfully trace the development of hallucinations across all model layers. By focusing on how models process symbolic triggers, we analyze five models using HaluEval and TruthfulQA. Our symbolic knowledge approach reveals that attention variance for these linguistic elements explodes to critical instability in early layers (2-4), with negation triggering catastrophic variance levels, demonstrating that symbolic semantic processing breaks down from the very beginning. Through the lens of symbolic linguistic knowledge, despite larger model sizes, hallucination rates remain consistently high (78.3%-83.7% across Gemma variants), with steep attention drops for symbolic semantic triggers throughout deeper layers. Our findings demonstrate that hallucination is fundamentally a symbolic linguistic processing failure, not a general generation problem, revealing that symbolic semantic knowledge provides the key to understanding and localizing hallucination mechanisms in LLMs.

Future superhuman models will surpass the ability of humans and humans will only be able to \textit{weakly} supervise superhuman models. To alleviate the issue of lacking high-quality data for model alignment, some works on weak-to-strong generalization (W2SG) finetune a strong pretrained model with a weak supervisor so that it can generalize beyond weak supervision. However, the invariable use of weak supervision in existing methods exposes issues in robustness, with a proportion of weak labels proving harmful to models. In this paper, we propose a selective W2SG framework to avoid using weak supervision when unnecessary. We train a binary classifier P(IK) to identify questions that a strong model can answer and use its self-generated labels for alignment. We further refine weak labels with a graph smoothing method. Extensive experiments on three benchmarks show that our method consistently outperforms competitive baselines. Further analyses show that P(IK) can generalize across tasks and difficulties, which indicates selective W2SG can help superalignment.

Large Language Models (LLMs) inherit explicit and implicit biases from their training datasets. Identifying and mitigating biases in LLMs is crucial to ensure fair outputs, as they can perpetuate harmful stereotypes and misinformation. This study highlights the need to address biases in LLMs amid growing generative AI. We studied bias-specific benchmarks such as StereoSet and CrowSPairs to evaluate the existence of various biases in multiple generative models such as BERT and GPT 3.5. We proposed an automated Bias-Identification Framework to recognize various social biases in LLMs such as gender, race, profession, and religion. We adopted a two-pronged approach to detect explicit and implicit biases in text data. Results indicated fine-tuned models struggle with gender biases but excelled at identifying and avoiding racial biases. Our findings illustrated that despite having some success, LLMs often over-relied on keywords. To illuminate the capability of the analyzed LLMs in detecting implicit biases, we employed Bag-of-Words analysis and unveiled indications of implicit stereotyping within the vocabulary. To bolster the model performance, we applied an enhancement strategy involving fine-tuning models using prompting techniques and data augmentation of the bias benchmarks. The fine-tuned models exhibited promising adaptability during cross-dataset testing and significantly enhanced performance on implicit bias benchmarks, with performance gains of up to 20%.

In this research, we combine Transformer-based relation extraction with matching of knowledge graphs (KGs) and apply them to answering multiple-choice questions (MCQs) while maintaining the traceability of the output process. KGs are structured representations of factual knowledge consisting of entities and relations. Due to the high construction cost, they had been regarded as static databases with validated links. However, the recent development of Transformer-based relation extraction (RE) methods has enabled us to generate KGs dynamically by giving them natural language texts, and thereby opened the possibility for representing the meaning of the input sentences with the created KGs. Using this effect, we propose a method that answers MCQs in the "fill-in-the-blank" format, taking care of the point that RE methods generate KGs that represent false information if provided with factually incorrect texts. We measure the truthfulness of each question sentence by (i) converting the sentence into a relational graph using an RE method and (ii) verifying it against factually correct KGs under the closed-world assumption. The experimental results demonstrate that our method correctly answers up to around 70% of the questions, while providing traceability of the procedure. We also highlight that the question category has a vast influence on the accuracy.

Abstract--Video Moment Retrieval is a task in video understanding that aims to localize a specific temporal segment in an untrimmed video based on a natural language query. Despite recent progress in moment retrieval from videos using both traditional techniques and Multimodal Large Language Models (MLLM), most existing methods still rely on coarse temporal understanding and a single visual modality, limiting performance on complex videos. T o address this, we introduce Shot-aware Multimodal Audio-enhanced Retrieval of Temporal Segments (SMART), an MLLM-based framework that integrates audio cues and leverages shot-level temporal structure. SMART enriches multimodal representations by combining audio and visual features while applying Shot-aware T oken Compression, which selectively retains high-information tokens within each shot to reduce redundancy and preserve fine-grained temporal details. We also refine prompt design to better utilize audio-visual cues. Evaluations on Charades-ST A and QVHighlights show that SMART achieves significant improvements over state-of-the-art methods, including a 1.61% increase in R1@0.5 and 2.59% gain in R1@0.7 on Charades-ST A. Index T erms--Video Moment Retrieval, T emporal Localization, Audio-Visual Representation Learning, Shot-aware T oken Compression, Shot Boundary Detection, T emporal Reasoning, Multimodal Large Language Models (MLLM), Video Understanding. ITH the rapid growth of video content shared and created on the internet and social media, the ability to efficiently analyze such content has become increasingly important. One key task in this domain is moment retrieval-- the process of identifying the specific temporal segment within a video that best corresponds to a given natural language query.

Abstract--Fine-grained identification of IDS-flagged suspicious traffic is crucial in cybersecurity. In practice, cyber threats evolve continuously, making the discovery of novel malicious traffic a critical necessity as well as the identification of known classes. Recent studies have advanced this goal with deep models, but they often rely on task-specific architectures that limit transferability and require per-dataset tuning. In this paper we introduce MalRAG, the first LLM driven retrieval-augmented framework for open-set malicious traffic identification. MalRAG freezes the LLM and operates via comprehensive traffic knowledge construction, adaptive retrieval, and prompt engineering. Concretely, we construct a multi-view traffic database by mining prior malicious traffic from content, structural, and temporal perspectives. Furthermore, we introduce a Coverage-Enhanced Retrieval Algorithm that queries across these views to assemble the most probable candidates, thereby improving the inclusion of correct evidence. We then employ Traffic-A ware Adaptive Pruning to select a variable subset of these candidates based on traffic-aware similarity scores, suppressing incorrect matches and yielding reliable retrieved evidence. Moreover, we develop a suite of guidance prompts where task instruction, evidence referencing, and decision guidance are integrated with the retrieved evidence to improve LLM performance. Across diverse real-world datasets and settings, MalRAG delivers state-of-the-art results in both fine-grained identification of known classes and novel malicious traffic discovery. Ablation and deep-dive analyses further show that MalRAG effective leverages LLM capabilities yet achieves open-set malicious traffic identification without relying on a specific LLM. ITH With the rapid evolution of network applications, malicious traffic has grown more dynamic and concealed, escalating operational risks and complicating network defense [1], [2].

Timely and accurate pre-arrival video streaming and analytics are critical for emergency medical services (EMS) to deliver life-saving interventions. Yet, current-generation EMS infrastructure remains constrained by one-to-one video streaming and limited analytics capabilities, leaving dispatchers and EMTs to manually interpret overwhelming, often noisy or redundant information in high-stress environments. We present TeleEMS, a mobile live video analytics system that enables pre-arrival multimodal inference by fusing audio and video into a unified decision-making pipeline before EMTs arrive on scene. TeleEMS comprises two key components: TeleEMS Client and TeleEMS Server. The TeleEMS Client runs across phones, smart glasses, and desktops to support bystanders, EMTs en route, and 911 dispatchers. The TeleEMS Server, deployed at the edge, integrates EMS-Stream, a communication backbone that enables smooth multi-party video streaming. On top of EMSStream, the server hosts three real-time analytics modules: (1) audio-to-symptom analytics via EMSLlama, a domain-specialized LLM for robust symptom extraction and normalization; (2) video-to-vital analytics using state-of-the-art rPPG methods for heart rate estimation; and (3) joint text-vital analytics via PreNet, a multimodal multitask model predicting EMS protocols, medication types, medication quantities, and procedures. Evaluation shows that EMSLlama outperforms GPT-4o (exact-match 0.89 vs. 0.57) and that text-vital fusion improves inference robustness, enabling reliable pre-arrival intervention recommendations. TeleEMS demonstrates the potential of mobile live video analytics to transform EMS operations, bridging the gap between bystanders, dispatchers, and EMTs, and paving the way for next-generation intelligent EMS infrastructure.

Automatic ICD coding from clinical text is a critical task in medical NLP but remains hindered by the extreme long-tail distribution of diagnostic codes. Thousands of rare and zero-shot ICD codes are severely underrepresented in datasets like MIMIC-III, leading to low macro-F1 scores. In this work, we propose a data-centric framework that generates high-quality synthetic discharge summaries to mitigate this imbalance. Our method constructs realistic multi-label code sets anchored on rare codes by leveraging real-world co-occurrence patterns, ICD descriptions, synonyms, taxonomy, and similar clinical notes. Using these structured prompts, we generate 90,000 synthetic notes covering 7,902 ICD codes, significantly expanding the training distribution. We fine-tune two state-of-the-art transformer-based models, PLM-ICD and GKI-ICD, on both the original and extended datasets. Experiments show that our approach modestly improves macro-F1 while maintaining strong micro-F1, outperforming prior SOT A. While the gain may seem marginal relative to the computational cost, our results demonstrate that carefully crafted synthetic data can enhance equity in long-tail ICD code prediction.

Reasoning-augmented Vision-Language Models (RVLMs) rely on safety alignment to prevent harmful behavior, yet their exposed chain-of-thought (CoT) traces introduce new attack surfaces. In this work, we find that the safety alignment of RVLMs can be easily break through a novel attack method termed \textbf{Stealth Fine-Tuning}. Our method elicits harmful reasoning traces through \textbf{segment-level interference} and reuses the self-generated outputs as supervised fine-tuning data. Through a \textbf{turn-based weighted} loss design, yielding a lightweight, distribution-consistent finetuning method. In our experiment, with only 499 samples and under 3 hours on a single A100 (QLoRA), Stealth Fine-Tuning outperforms IDEATOR by 38.52\% ASR while preserving general reasoning ability, as the tuned model retains the original representation distribution. Experiments on AdvBench and several general benchmarks demonstrate that Stealth Fine-Tuning is a low-cost and highly effective way to bypass alignment defenses. \textcolor{red}{\textbf{Disclaimer: This paper contains content that may be disturbing or offensive.}}