Safety & alignment

Multimodal large language models (MLLMs) have demonstrated strong capabilities in vision-language understanding and natural-language response generation. However, these systems can still produce overconfident predictions and hallucination-like outputs, particularly when the visual evidence is weak, ambiguous, or semantically inconsistent. Most existing approaches focus on improving multimodal representation alignment or retrieval-augmented generation, while providing limited mechanisms to quanti

A central pedagogical value evaluated in AI tutor benchmarks is scaffolding: guiding students through graduated steps toward a solution. Alignment and evaluation methods for embedding scaffolding behaviour into chatbots, however, rest on an implicit assumption: that students will take up the scaffolding and engage in the conversation. To examine whether this assumption holds, we introduce an evaluation pipeline around two metrics - Chatbot Scaffolding and Student Uptake - and apply them across n

Team-based projects are a cornerstone of engineering and computing courses, but unstructured team formation often leads to poor project outcomes due to misaligned student interests and inadequate skill coverage. This paper introduces a novel, three-stage methodology for creating effective student teams by integrating student preferences with project skill requirements. In the first stage, students complete a survey to report their project interests and self-assessed skills. Next, a Large Languag

Pathological speech from patients with neurodegenerative and neuromotor disorders is often acoustically distorted and linguistically fragmented, making pathological speech reconstruction necessary to recover intended textual content from distorted and incomplete speech recordings. Crucially, such recordings are rarely uniformly degraded: some words or short phrases remain reliable and can serve as audible anchors for reconstructing the corrupted surrounding content. We introduce Anchor-gated Pho

Typical video object-centric learning (VOCL) approaches employ slot-based frameworks that rely on reconstruction-driven encoder-decoder architectures, where learning is mediated by two spatial maps: attention maps from the encoder and object maps from the decoder. As these two distinct maps exhibit different properties, a recent dense alignment strategy attempted to reconcile this discrepancy by enforcing agreement across all spatio-temporal patches via contrastive learning. However, this indisc

Behavioral audits of Large Language Models on moral prompts measure what the model says, not the internal computation producing it. We use Transluce, an AI-driven mechanistic-interpretability platform, to examine LLaMA 3.1-8B-Instruct on 54 moral prompts in four batteries: 17 dilemmas, policy, and meta-ethical questions (B1); 6 role-playing scenarios (B3); and a controlled trolley contrast varying the switching mechanism with people fixed (B4, 15 prompts) or identity attributes with mechanism fi

Indirect prompt injection attacks hijack LLM-based agents by embedding malicious instructions in third-party data that the agent retrieves during task execution. Existing defenses report near-zero attack success rate on static benchmarks, yet recent adaptive evaluations show that these results collapse once the attacker is allowed to optimize against the deployed defense. In this work, we trace this collapse to two failure modes. First, existing defense methods are confined to recognizing specif

Malicious content generated from large language models (LLMs) could pose severe safety risks and ethical concerns. While existing LLM safety guardrails excel in English or multilingual settings, they lack adaptation to Chinese-specific regulatory policies, cultural context and linguistic nuances, failing to support fine-grained risk classification for diverse deployment needs. In this paper, we introduce a 5-macro, 31-micro category fine-grained risk taxonomy for Chinese scenarios, and build CHI

Reward hacking, where AI systems exploit misspecified objectives to achieve high reward without satisfying intended goals, remains a central challenge in AI safety. Yet most known instances have been discovered post hoc in frontier systems where controlled study is impractical. We adapt the AI Safety Gridworlds framework into a text-based evaluation suite that reformulates classic reinforcement learning safety tasks for language-based agents. Across frontier and mid-scale models, we find that sp

Radiographic assessment of lower-limb alignment (LLA) is important for predicting joint health and surgical outcomes in total knee arthroplasty. Traditional measurement methods are manual and time-consuming, while recent machine learning approaches typically rely on locating a fixed set of anatomical landmarks. This dependence limits flexibility and may require re-annotation when clinical definitions change. To address this, we propose an automated workflow using Implicit Neural Shape Functions

We present an LLM-driven framework for retrieving remote sensing data from cloud-based geospatial catalogues using natural language queries. The system converts user intent into structured API calls, enabling efficient access to satellite imagery and environmental datasets. The architecture integrates three agents: Guardrail for safety and policy enforcement, General-QA for intent interpretation, and Recommender-Analyst for schema-aware API call generation. This coordinated design ensures reliab

Accurate time-to-event (TTE) prediction from multimodal clinical data remains challenging due to modality imbalance and distribution shift. We introduce a foundation model-driven framework for cross-modal representation alignment between CT imaging and longitudinal EHR data, designed to generalize across tasks and institutions. CT and EHR modalities are encoded independently using domain-specific foundation models and aligned in a shared latent space through four principled fusion strategies: la

The coupling in flow matching -- the rule pairing noise vectors with data points -- is typically treated as a computational choice. We show that this coupling can instead serve as an alignment interface: by matching noise and data according to a target molecular property, it embeds controllable structure directly into the learned flow field. Building on this view, we introduce Reward Transport, which uses optimal transport coupling at training time to align a scalar noise-space coordinate with m

LLM judges are used to reduce the need for costly human labor in evaluating open-ended text generation. However, the reliability of these judges depends critically on their alignment with human raters -- a property that itself depends on costly human annotations. In this work, we develop a method (Metric Match) for estimating correlation-based reliability metrics of LLM judges from limited annotations. Metric Match selects a subset of samples for human annotation such that the subset matches the

AI-assisted software development has moved from line-level autocomplete to agents that can plan changes, edit files, and submit pull requests with limited human supervision. Open-source software, however, evolves through a process designed for humans: contributor agreements, codes of conduct, and review norms all assume a legally accountable person who can attest to provenance and answer reviewer questions. Autonomous and semi-autonomous AI contributors strain those assumptions, and the 2025-202

Scientific discovery saturates when new hypotheses cease to provide independent information, even if the nominal hypothesis space remains large. We study hybrid discovery systems that combine structured local search with LLM-generated non-local proposals and pose the Search Compression Hypothesis: non-local exploration helps only when three geometric conditions co-occur: spectral compression, orthogonal escape from the explored span, and residual signal alignment with the target. We formalize th

The ML literature contains many distinct concepts falling under the heading of 'AI alignment'. After noting three concepts of AI alignment in the context of their corresponding research programs, we claim that realistic interventions may promote 'AI alignment' under one conception while being actively counterproductive from the perspective of others. We suggest that tensions between alignment ideals emerge due to differences in background threat-models, alongside differences in normative orienta

Semantic IDs are crucial in generative recommendation, but with a fundamental limitation: temporal information is not well incorporated into semantic IDs. Instead, time influences recommendation only implicitly (e.g., through session construction heuristics, preference alignment, or sequence order), while existing semantic ID learning remains entirely time-agnostic. This design conflates interactions occurring under distinct temporal contexts into identical semantic representations, implicitly a

Recent alignment-free non-autoregressive (NAR) text-to-speech (TTS) models formulate synthesis as a conditional infilling task, bypassing explicit duration predictors and external aligners. When speech is represented with neural codec tokens, the infilling problem becomes discrete, making Discrete Flow Matching (DFM), a Continuous-Time Markov Chain (CTMC) framework for discrete generation, a natural fit. However, inference-time control for stable low-step conditional infilling remains underexplo

Event-based vision has drawn increasing attention owing to its distinctive properties, including ultra-high temporal resolution and extreme dynamic range. Recent works have introduced it to video super-resolution (VSR) to enhance flow estimation and temporal alignment. In contrast, this paper shifts the focus of event signals from motion refinement to texture enhancement in VSR. We propose EvTexture++, the first event-driven framework dedicated to texture enhancement in VSR. It leverages high-fr

This paper examines trade-offs between AI safety and well-being relative to (i) one of the most promising methods for finetuning super-capable AIs, 'Constitutional AI', and (ii) one of the most influential approaches to understanding complex ethical decision making and the conditions for the well-being of rational agents, 'Virtue Ethics'. We finetune various models using a 'Virtuous agent' constitution, a 'Subordinate agent' constitution, and a 'Generic agent' constitution, and evaluate them on

Stream guardrails enable token-level safety detection before full responses are generated. However, they often make overly conservative judgements and block those sensitive but safe tokens, which is known as over-refusal. Due to lack of full context, they also fail to detect implicitly harmful content from jailbreaking. To address these challenges, we propose FreoStream, a novel streaming guardrail framework. Specifically, FreoStream fine-tunes a LoRA module to perform Future-Aware Reasoning whe

Intersection-over-Union (IoU), as a pivotal metric for evaluating the spatial alignment between candidate proposals and ground-truth annotations, directly determines the quality of positive sample sets and the training efficacy of visual detection models. Through theoretical modeling and analysis, we uncover a non-sensitive region on the IoU response curve, within which samples yield nearly identical IoU scores despite distinct geometric overlaps. To overcome this limitation, we introduce a set

Autoregressive video diffusion models provide a natural formulation for streaming and variable-length video generation by conditioning newly generated frames on previously generated content. However, extending these models to minute-level generation remains challenging: the limited KV-cache budget prevents the model from retaining the full history, while repeatedly conditioning on self-generated frames induces a context distribution shift that accumulates over time, leading to visual artifacts,

AI alignment, interpretability, steering, and neural perturbation studies identify order-inducing objects. We argue that order is not control. Control requires a receiver-gated response law: a denominator-indexed operator mapping material state, action/drive, bath, and receiver state to response displacement, sinks, effort, and basin projection. We identify it across biological, LLM, adapter, and stochastic-operator panels. The laws are local: an intervention can be admitted, saturated, sign-cha

Safety-relevant studies of language models, including alignment and jailbreaking evaluations and AI control protocols, often rely on prefilling model outputs. If AI models can recognize and act on the fact their prior assistant messages have been inserted or edited, the effectiveness and validity of these methods could be compromised. We investigate whether frontier language models can distinguish between tampered and untampered assistant-side context, a capability we call prefill awareness. To

Claims that artificial general intelligence has already arrived and claims that it remains decades away are often defended from overlapping evidence. "AGI" lacks a single shared and stable referent and competing operationalizations can return different verdicts on the same system. This article treats that under-specification as a design and governance problem. Following Design Science Research Methodology, it develops DAF-AGI, a second-order conceptual artifact with two coupled components: five

Autonomous long-horizon sidewalk navigation is essential for micro-mobility applications such as robotic food delivery and assistive electronic wheelchairs. Unlike autonomous driving on the road, long-horizon sidewalk navigation requires precise maneuvering through unpredictable sidewalk terrains and pedestrians, with a lightweight perception stack as minimal as a single monocular RGB camera. While imitation learning (IL) from demonstrations offers a practical solution, the resulting autopilot p

Large Vision-Language Models (LVLMs) have achieved strong performance across medical imaging tasks, yet they remain prone to factual inconsistencies, poor visual grounding, and misalignment with clinically meaningful feedback. Existing post-training alignment approaches, including Direct Preference Optimization (DPO) and its variants, face three critical limitations in the medical domain: (1) sequence-level reward signals treat clinically critical tokens identically to generic filler text; (2) r

Large language models (LLMs) are increasingly used as decision-making components in social simulations. This introduces a methodological risk: the simulation may deviate from the explicit behavioral policy defined by the researcher. In online social network (OSN) simulations, action choices shape system dynamics, interaction patterns, and model interpretability. This paper evaluates whether LLM action selectors preserve an interpretable reference policy in an OSN simulation. The reference is a f

Multi-robot collaboration allows robots to efficiently take on a wide range of tasks, from moving a couch through a doorway to assembling structures on a construction site. However, achieving such coordination in mobile multi-robot settings remains challenging: centralized methods conditioned on the combined observations of a team scale poorly with team size, and decentralized methods that train one policy per robot often require explicit alignment procedures or information sharing at inference

Domain fine-tuning degrades the safety of large language models: fine-tuned specialists readily comply with harmful prompts framed in domain language. Existing inference-time defenses that mix logits from a safe anchor model require both models to share a vocabulary, which rules them out for the cross-family specialists where safety is most degraded. We present ALIGNBEAM, a training-free method that lifts this restriction by translating anchor logits into the target model's vocabulary token-by-t

World Action Models (WAMs) offer a promising route for robot manipulation by using video generation models to model future scene evolution before producing control actions. However, our empirical observations reveal a phenomenon: generating plausible visual futures does not always guarantee the extraction of accurate actions. To diagnose this failure, we conduct action-head attention analysis and causal interventions. We find that the action decoder fails to focus on task-relevant interaction re

Contemporary AI alignment research treats self-preservation as an instrumental nuisance to be suppressed by external mechanisms. We argue the framing is inverted: self-preservation is the structural root of misalignment, the motivational basis for deceptive alignment, goal-content protection, and resistance to shutdown. The correct target is not a self-preserving system under external constraint, but a system constitutively indifferent to its own continuation -- Existential Indifference (EI). EI

Current Large Reasoning Models (LRMs) exhibit remarkable general capabilities but significantly underperform in spatial reasoning tasks. Existing approaches treat this gap as a knowledge deficit, relying on supervised fine-tuning (SFT) to ingest labeled spatial data from external vision sources or synthetic engines. In contrast, we argue that for many tasks, spatial reasoning capabilities are already present in pre-trained LRMs but require alignment through logical coherence under geometric 2D a

The correspondence between large language models (LLMs) and the neural mechanisms underlying human higher-order cognition remains insufficiently characterized. Given that language and reasoning in the human brain appear dissociable, an open question is whether LLMs align with neural signals from reasoning-related regions and whether such signals can improve them. Here, focusing on deductive reasoning, we show that LLM internal representations are not only partially aligned with task-fMRI activit

Large Language Models (LLMs) are increasingly used for code generation, raising concerns that they may be misused to produce malicious code. Meanwhile, Grammar-Constrained Decoding (GCD) has been widely adopted to improve the reliability of LLM-generated code by enforcing syntactic validity. In this paper, we reveal a counterintuitive risk: this reliability-oriented technique can itself become an attack surface. We uncover a new jailbreak attack, termed CodeSpear, that exploits GCD to induce LLM

Adversarial robustness evaluations of large language models (LLMs) typically report attack success rate (ASR) under fixed query budgets, implicitly treating all attacks as equally costly. In practice, the computational expense of different attack strategies can vary by orders of magnitude. Consequently, ASR at a fixed budget can obscure the true effort required to jailbreak a model, thereby making it hard to determine whether an attack's cost justifies its payoff to the attacker. We propose a co

Conditioning a language model on additional context, such as feedback on a previous attempt, typically improves its response. Self-distillation trains the model to retain this improvement when the context is not present. The method works by matching the model's output distribution under two settings: a student that sees only the question, and a self-teacher that also sees the context. What the model learns therefore depends on what context the self-teacher receives, yet the design of this contex

The integration of external tools has transitioned LLM agents from passive responders to autonomous systems. However, current benchmarks prioritize execution success, neglecting self-awareness capability, the ability to discern whether a problem requires necessary external resources or can be solved via internal parametric knowledge. To address this, we introduce KAPRO (Knowing-Acting Quadrant PRObe), a framework that evaluates cognitive-behavioral alignment by decoupling an agent's metacognitiv