Recent advances in Large Language Models (LLMs) have enabled unprecedented capabilities for time-series reasoning in diverse real-world applications, including medical, financial, and spatio-temporal domains. However, existing approaches typically focus on task-specific model customization, such as forecasting and anomaly detection, while overlooking the data itself, referred to as time-series primitives, which are essential for in-depth reasoning. This position paper advocates a fundamental shift in approaching time-series reasoning with LLMs: prioritizing alignment paradigms grounded in the intrinsic primitives of time series data over task-specific model customization. This realignment addresses the core limitations of current time-series reasoning approaches, which are often costly, inflexible, and inefficient, by systematically accounting for intrinsic structure of data before task engineering. To this end, we propose three alignment paradigms: Injective Alignment, Bridging Alignment, and Internal Alignment, which are emphasized by prioritizing different aspects of time-series primitives: domain, characteristic, and representation, respectively, to activate time-series reasoning capabilities of LLMs to enable economical, flexible, and efficient reasoning. We further recommend that practitioners adopt an alignment-oriented method to avail this instruction to select an appropriate alignment paradigm. Additionally, we categorize relevant literature into these alignment paradigms and outline promising research directions.

Models of human feedback for AI alignment, such as those underpinning Direct Preference Optimization (DPO), often bake in a singular, static set of preferences, limiting adaptability. This paper challenges the assumption of monolithic preferences by introducing Configurable Preference Tuning (CPT), a novel framework for endowing language models with the ability to dynamically adjust their behavior based on explicit, human-interpretable directives. CPT leverages synthetically generated preference data, conditioned on system prompts derived from structured, fine-grained rubrics that define desired attributes like writing style. By fine-tuning with these rubric-guided preferences, the LLM learns to modulate its outputs at inference time in response to the system prompt, without retraining. This approach not only offers fine-grained control but also provides a mechanism for modeling more nuanced and context-dependent human feedback. Several experimental artifacts, such as training code, generated datasets and fine-tuned models are released at https://github.com/vicgalle/configurable-preference-tuning

Multimodal large language models (MLLMs), which bridge the gap between audio-visual and natural language processing, achieve state-of-the-art performance on several audio-visual tasks. Despite the superior performance of MLLMs, the scarcity of high-quality audio-visual training data and computational resources necessitates the utilization of third-party data and open-source MLLMs, a trend that is increasingly observed in contemporary research. This prosperity masks significant security risks. Empirical studies demonstrate that the latest MLLMs can be manipulated to produce malicious or harmful content. This manipulation is facilitated exclusively through instructions or inputs, including adversarial perturbations and malevolent queries, effectively bypassing the internal security mechanisms embedded within the models. To gain a deeper comprehension of the inherent security vulnerabilities associated with audio-visual-based multimodal models, a series of surveys investigates various types of attacks, including adversarial and backdoor attacks. While existing surveys on audio-visual attacks provide a comprehensive overview, they are limited to specific types of attacks, which lack a unified review of various types of attacks. To address this issue and gain insights into the latest trends in the field, this paper presents a comprehensive and systematic review of audio-visual attacks, which include adversarial attacks, backdoor attacks, and jailbreak attacks. Furthermore, this paper also reviews various types of attacks in the latest audio-visual-based MLLMs, a dimension notably absent in existing surveys. Drawing upon comprehensive insights from a substantial review, this paper delineates both challenges and emergent trends for future research on audio-visual attacks and defense.

Large Vision-Language Models (LVLMs) have demonstrated impressive multimodal abilities but remain prone to multilingual object hallucination, with a higher likelihood of generating responses inconsistent with the visual input when utilizing queries in non-English languages compared to English. Most existing approaches to address these rely on pretraining or fine-tuning, which are resource-intensive. In this paper, inspired by observing the disparities in cross-modal attention patterns across languages, we propose Cross-Lingual Attention Intervention for Mitigating multilingual object hallucination (CLAIM) in LVLMs, a novel near training-free method by aligning attention patterns. CLAIM first identifies language-specific cross-modal attention heads, then estimates language shift vectors from English to the target language, and finally intervenes in the attention outputs during inference to facilitate cross-lingual visual perception capability alignment. Extensive experiments demonstrate that CLAIM achieves an average improvement of 13.56% (up to 30% in Spanish) on the POPE and 21.75% on the hallucination subsets of the MME benchmark across various languages. Further analysis reveals that multilingual attention divergence is most prominent in intermediate layers, highlighting their critical role in multilingual scenarios.

Coding remains one of the most fundamental modes of interaction between humans and machines. With the rapid advancement of Large Language Models (LLMs), code generation capabilities have begun to significantly reshape programming practices. This development prompts a central question: Have LLMs transformed code style, and how can such transformation be characterized? In this paper, we present a pioneering study that investigates the impact of LLMs on code style, with a focus on naming conventions, complexity, maintainability, and similarity. By analyzing code from over 19,000 GitHub repositories linked to arXiv papers published between 2020 and 2025, we identify measurable trends in the evolution of coding style that align with characteristics of LLM-generated code. For instance, the proportion of snake\_case variable names in Python code increased from 47% in Q1 2023 to 51% in Q1 2025. Furthermore, we investigate how LLMs approach algorithmic problems by examining their reasoning processes. Given the diversity of LLMs and usage scenarios, among other factors, it is difficult or even impossible to precisely estimate the proportion of code generated or assisted by LLMs. Our experimental results provide the first large-scale empirical evidence that LLMs affect real-world programming style.

Reinforcement learning (RL) with tree search has demonstrated superior performance in traditional reasoning tasks. Compared to conventional independent chain sampling strategies with outcome supervision, tree search enables better exploration of the reasoning space and provides dense, on-policy process rewards during RL training but remains under-explored in On-Policy LLM RL. We propose TreeRL, a reinforcement learning framework that directly incorporates on-policy tree search for RL training. Our approach includes intermediate supervision and eliminates the need for a separate reward model training. Existing approaches typically train a separate process reward model, which can suffer from distribution mismatch and reward hacking. We also introduce a cost-effective tree search approach that achieves higher search efficiency under the same generation token budget by strategically branching from high-uncertainty intermediate steps rather than using random branching. Experiments on challenging math and code reasoning benchmarks demonstrate that TreeRL achieves superior performance compared to traditional ChainRL, highlighting the potential of tree search for LLM. TreeRL is open-sourced at https://github.com/THUDM/TreeRL.

In-context learning (ICL) allows large language models (LLMs) to solve novel tasks without weight updates. Despite its empirical success, the mechanism behind ICL remains poorly understood, limiting our ability to interpret, improve, and reliably apply it. In this paper, we propose a new theoretical perspective that interprets ICL as an implicit form of knowledge distillation (KD), where prompt demonstrations guide the model to form a task-specific reference model during inference. Under this view, we derive a Rademacher complexity-based generalization bound and prove that the bias of the distilled weights grows linearly with the Maximum Mean Discrepancy (MMD) between the prompt and target distributions. This theoretical framework explains several empirical phenomena and unifies prior gradient-based and distributional analyses. To the best of our knowledge, this is the first to formalize inference-time attention as a distillation process, which provides theoretical insights for future prompt engineering and automated demonstration selection.

We surveyed 582 AI researchers who have published in leading AI venues and 838 nationally representative US participants about their views on the potential development of AI systems with subjective experience and how such systems should be treated and governed. When asked to estimate the chances that such systems will exist on specific dates, the median responses were 1% (AI researchers) and 5% (public) by 2024, 25% and 30% by 2034, and 70% and 60% by 2100, respectively. The median member of the public thought there was a higher chance that AI systems with subjective experience would never exist (25%) than the median AI researcher did (10%). Both groups perceived a need for multidisciplinary expertise to assess AI subjective experience. Although support for welfare protections for such AI systems exceeded opposition, it remained far lower than support for protections for animals or the environment. Attitudes toward moral and governance issues were divided in both groups, especially regarding whether such systems should be created and what rights or protections they should receive. Y et a majority of respondents in both groups agreed that safeguards against the potential risks from AI systems with subjective experience should be implemented by AI developers now, and if created, AI systems with subjective experience should treat others well, behave ethically, and be held accountable. Overall, these results suggest that both AI researchers and the public regard the emergence of AI systems with subjective experience as a possibility this century, though substantial uncertainty and disagreement remain about the timeline and appropriate response. Noemi Dreksler (corresponding author) can be reached under noemi.dreksler@governance.ai.

Recent advancements in large language models (LLMs) have shown promise for automated vulnerability detection and repair in software systems. This paper investigates the performance of GPT-4o in repairing Java vulnerabilities from a widely used dataset (Vul4J), exploring how different contextual information affects automated vulnerability repair (AVR) capabilities. We compare the latest GPT-4o's performance against previous results with GPT-4 using identical prompts. We evaluated nine additional prompts crafted by us that contain various contextual information such as CWE or CVE information, and manually extracted code contexts. Each prompt was executed three times on 42 vulnerabilities, and the resulting fix candidates were validated using Vul4J's automated testing framework. Our results show that GPT-4o performed 11.9\% worse on average than GPT-4 with the same prompt, but was able to fix 10.5\% more distinct vulnerabilities in the three runs together. CVE information significantly improved repair rates, while the length of the task description had minimal impact. Combining CVE guidance with manually extracted code context resulted in the best performance. Using our \textsc{Top}-3 prompts together, GPT-4o repaired 26 (62\%) vulnerabilities at least once, outperforming both the original baseline (40\%) and its reproduction (45\%), suggesting that ensemble prompt strategies could improve vulnerability repair in zero-shot settings.

The proliferation of deceptive content online necessitates robust Fake News Detection (FND) systems. While evidence-based approaches leverage external knowledge to verify claims, existing methods face critical limitations: noisy evidence selection, generalization bottlenecks, and unclear decision-making processes. Recent efforts to harness Large Language Models (LLMs) for FND introduce new challenges, including hallucinated rationales and conclusion bias. To address these issues, we propose \textbf{RoE-FND} (\textbf{\underline{R}}eason \textbf{\underline{o}}n \textbf{\underline{E}}xperiences FND), a framework that reframes evidence-based FND as a logical deduction task by synergizing LLMs with experiential learning. RoE-FND encompasses two stages: (1) \textit{self-reflective knowledge building}, where a knowledge base is curated by analyzing past reasoning errors, namely the exploration stage, and (2) \textit{dynamic criterion retrieval}, which synthesizes task-specific reasoning guidelines from historical cases as experiences during deployment. It further cross-checks rationales against internal experience through a devised dual-channel procedure. Key contributions include: a case-based reasoning framework for FND that addresses multiple existing challenges, a training-free approach enabling adaptation to evolving situations, and empirical validation of the framework's superior generalization and effectiveness over state-of-the-art methods across three datasets.