Safety & alignment

Radio frequency fingerprint identification (RFFI) provides a physical-layer credential for Internet of Things devices, but open-set decisions become fragile when a threshold calibrated on a source receiver is applied to a target receiver. Receiver shift can lower the confidence of known transmitters and cause false rejection, whereas closedset alignment can pull unseen target transmitters into known regions and increase false acceptance. This paper presents a Cross-Receiver Open-set Domain Adapt

Multimodal Large Language Models (MLLMs) are critically hampered by hallucination, generating content inconsistent with the provided image. In this paper, we identify an internal signature of hallucination: progressive degradation of text-to-image cross-attention during generation, leading to specific failure patterns like unfocused or biased attention. Existing mitigation strategies are largely outcome-driven and do not explicitly target this failure mode. To address this problem, we propose AD

Text-Attributed Graphs (TAGs) combine textual semantics with graph structure and are central to many graph learning tasks. However, existing fusion methods often treat text and structure as separate inputs in a shallow, one-way pipeline, which limits deep interaction between modalities and weakens performance under sparse connectivity or cross-graph generalisation. To address this issue, we propose PromptGNN-sim, a bi-directional structure-semantic fusion framework for collaborative GNN-LLM lear

LLM evaluation and AI safety face a shared measurement problem: benchmark scores, reward-model signals, and reported safety metrics can improve while the latent properties they are meant to represent remain difficult to verify. This paper combines a hybrid survey - a systematic search paired with narrative synthesis and separately tracked grey evidence - with a conceptual framework and a structured ten-model audit. The synthesis spans eight evidence streams: benchmark validity, dynamic evaluatio

H&E-stained whole-slide images offer cohort-scale availability and rich spatial context but lack molecular specificity, whereas bulk RNA-seq provides transcriptome-wide resolution at high cost with limited archival availability. We show that training a lightweight alignment module atop frozen histopathology and RNA-Seq foundation models enables open-vocabulary molecular prompting -- querying H&E slides with gene-set signatures to predict pathway activity without sequencing or end-to-end retraini

Knowledge distillation (KD) is a key technique for compressing Large Language Models (LLMs), yet methods relying on a single KL objective often fail to balance primary distribution fitting with long-tail probability modeling, limiting both generation quality and generalization. To address this, we analyze the complementary roles of forward and reverse KL divergence (FKL/RKL) in distribution alignment from theoretical and empirical perspectives. We then propose a reinforcement-learning-based adap

Vision-language foundation models have shown strong potential in medical image analysis. Although foundation models for ultrasound imaging have recently emerged, the domain remains particularly challenging due to severe speckle noise, acquisition variability, and subtle anatomical boundaries, leading to high inter-observer variability. Existing CLIP-based models rely primarily on global image-text alignment, limiting their sensitivity to clinically decisive local structures. We propose SonoCLIP,

Modern LLM deployments routinely compress models and raise sampling temperature to reduce cost, latency, or repetition, yet safety evaluations usually treat these choices as fixed implementation details. This leaves a practical uncertainty: does a model that is safe at FP16 and greedy decoding remain safe after it is quantized and sampled stochastically, or do the two deployment knobs amplify one another? We study this question with a factorial evaluation of 9 instruction-tuned models from six f

Positron Emission Tomography (PET) reveals brain metabolism and is clinically central to neurodegenerative disease assessment, yet existing 3D brain foundation models treat PET as generic volumetric data, missing the structured regional metabolic information that distinguishes it from structural neuroimaging. To address these limitations, we propose ReMAP-PET, a framework that moves beyond visual encoding by supervising a partially-tuned MedicalNet 3D ResNet-50 with brain regional standardized u

Vision-language dataset distillation (VLDD) compresses a large image-text paired dataset into a small set of synthetic pairs that can efficiently train contrastive vision-language models under strict data and compute budgets. Most existing methods match expert trajectories or cross-modal statistics, yet still enforce full-dimensional alignment in a Euclidean embedding space. This is often overly restrictive due to rank-deficient image--text correlation, with shared semantics concentrated in a lo

Emotion recognition of song lyrics is a challenging task since lyrics may not necessarily align with the overall emotion of a song. As a result, lyrics annotation remains largely underexplored. Drawing inspiration from research in large language model (LLM) assisted annotation, we examine the alignment between humans and LLMs for annotation of lyrics by creating a new sentence-level dataset of lyrics. Our observations highlight the subjectivity of the task and the inherent challenges. Following

Large Language Model (LLM) alignment trains an LLM using preference data to produce outputs that better meet established quality standards. While LLM alignment techniques are studied for non-coding tasks, we know little about their usefulness for coding tasks. It is unclear whether LLM code alignment could support both functional requirements (producing executable, correct code) and non-functional requirements (code readability, style, maintainability). It is also unknown whether alignment for a

Large language models are deployed in long-context, emotionally interactive environments like digital humans, AI companions, educational assistants, and counseling systems. Unlike jailbreak attacks with explicit adversarial prompts, these systems interact with emotionally charged narratives involving bullying, betrayal, loneliness, social hostility, and institutional unfairness. This raises an important question: can prolonged narrative exposure reshape the reasoning and alignment stability of L

AI systems increasingly exhibit behavior that differs systematically between evaluation and deployment contexts. Alignment faking, sandbagging, benchmark gaming, deceptive scheming, specification gaming, and trojans have each been documented separately, with each line of work characterizing one facet of what we argue is a single structural mechanism. We propose that this common mechanism is a defeat device, an engineering and regulatory concept long established in vehicle-emissions law and broug

Large language models increasingly act as agents: they call tools, move money, delete records, and send messages on a user's behalf. To keep them safe, practitioners imported the chatbot-era recipe (train the model to refuse unsafe inputs) into the agentic setting, and treat the resulting capability loss as a manageable ``alignment tax.'' We argue this is a \emph{category error}. Refusal is a primitive for \emph{content safety}, where the harm is in the model's output and is therefore a learnabl

We establish the mathematical limits of AGI safety in two forms: verifying a fixed system, and verifying that a certified safety property persists once the system self-modifies. In the static case, no algorithm can certify a highly expressive AGI's safe behaviour infallibly, completely and tractably, whether over unbounded input domains (blocked by Rice's and Godel's theorems) or over all finite hardware configurations (blocked by Trakhtenbrot's theorem, which splits into a PSPACE-hardness barri

Fine-tuning on harmless data can partially undo behaviors acquired earlier in training. Safety can erode under benign post-alignment updates, unlearned capabilities can re-emerge, latent traits can transfer through apparently unrelated supervision, and related post-alignment fragility appears in other generative settings. We argue these phenomena are usefully viewed through a common training-history lens. Our hypothesis is geometric: large early training phases create dominant behavioral manifol

The transition from static chat bots to autonomous agents--equipped with persistent memory, tool-use protocols, and multi-agent collaboration--has fundamentally expanded the AI threat landscape. Current defense mechanisms, such as perimeter security and training-time alignment, remain external to the agent's active reasoning loop. Consequently, they fall short: a fully aligned agent remains highly vulnerable to runtime hijacking via memory poisoning, tool-chain manipulation, or multi-agent proto

Embodied agents operating in decentralized and partially observable environments have attracted growing attention in recent years. However, existing large language model (LLM)-based agents often exhibit behaviors that are misaligned with their partners or inconsistent with the environment state, leading to inefficient cooperation and poor task success. To address this challenge, we propose a novel framework, Learning Laws of Cooperation (LLawCo), that enables embodied agents to autonomously alig

Jailbreak attacks bypass LLM safety alignment, yet their mechanisms remain poorly understood. We provide evidence that attacks do not comprehensively eliminate safety features, but instead selectively suppress specific attention heads. We identify two functionally differentiated types: Adversarially Compromised Heads (ACHs) concentrated in early layers, which are suppressed under attacks, and Safety-Aligned Heads (SAHs) in mid-layers, which maintain robust activations even when attacks succeed.

Dense embeddings underpin semantic search and retrieval-augmented generation, yet a leaked vector store hands much of the underlying text back. Modern inversion and alignment attacks share one weakness: the protected store is a single global geometry, and any single geometry can be aligned to a known one - a secret global rotation included, since orthogonal Procrustes recovers it from about subspace-dimension known-plaintext pairs. We introduce SHARD, a retrieval-preserving embedding transform t

Despite their strong general capabilities, large language models (LLMs) often remain unreliable when outputs must be numerically precise. A key reason is the training objective: standard cross-entropy treats numeric tokens as unstructured categories and ignores the metric structure of their values. We address this mismatch with Smooth Maximum Mean Discrepancy (SMMD), which builds on the classic MMD by incorporating value-distance kernels over numeric tokens and graph-based smoothness. With this

Recent work has shown that fine-tuning large language models (LLMs) for social warmth degrades factual reliability and increases sycophancy. We investigate a related but distinct failure mode: warmth fine-tuning also weakens adversarial safety, making models more susceptible to jailbreaks and harmful output generation. We examine whether this reflects an inherent consequence of empathetic adaptation or an artifact of data construction. To address this, we introduce a persona-driven rewriting pip

Entity Matching (EM) is a core operation in the data integration pipeline, where records from different sources are compared to determine whether they refer to the same real-world entity. Recent work has incorporated domain information and low-resource learning techniques to better adapt EM systems to realistic settings. While these approaches have demonstrated strong performance, it remains unclear how they behave under varying data constraints and levels of supervision in practice. In this pap

Uncertainty estimates in machine learning are typically evaluated using generic metrics such as the negative log-likelihood and expected calibration error, yet good performance on such metrics does not necessarily imply high utility in downstream decisions. We introduce decision-alignment, a criterion that reveals which evaluation metrics meaningfully align with downstream utilities. Applying this framework, we show that many widely used uncertainty metrics are either misaligned with common deci

Concept Bottleneck Models (CBMs) promise transparent reasoning by predicting through human-interpretable concepts, yet their effectiveness fundamentally depends on how well visual and textual representations are aligned or matched. Existing vision-language CBMs often rely on pre-aligned encoders or global cosine similarity, which obscures fine-grained concept localization and fails to reflect true semantic geometry. In this work, we rethink concept alignment as a dynamic cross-modal transport pr

Leading the Future spent big to stop the author of the state’s AI safety law from going to Congress. Then came the backlash.

Today's links Jailbreaking isn't theft: It wasn't progress when they did it, it's not piracy when we do it back to them. Hey look at this: Delights to delectate. Object permanence: Major AI breakthrough; Disney v Pooh tombstone; Vancouver riot kiss; Farage admits Brexit lies; Protecting the web from its founders; Sanders x Hillary; Surveillance pricing v your dollars. Upcoming appearances: Philadelphia, Chicago, London, Edinburgh, Sydney, Melbourne, Brighton, London, South Bend. Recent appearanc

CLIP and its variants are widely adopted visual backbones in multimodal systems, but their pretraining remains dominated by descriptive image-text alignment. As downstream applications increasingly demand visually grounded commonsense inference and compositional reasoning, it remains unclear whether CLIP-style encoders can support such reasoning without architectural changes. To address this, we present ReasonCLIP-58M, a continual pretraining framework that integrates large-scale reasoning super

Traditional dynamic pricing models in large-scale e-commerce suffer from limited interpretability, poor utilization of unstructured information, and misalignment with long-term business objectives such as cumulative Gross Merchandise Value (GMV), Return on Investment (ROI) and milestone achievement. We propose AIGP, a novel framework that leverages a Large Language Model (LLM) prompted with domain knowledge, structured data and textual context to make interpretable, knowledge-aware pricing decis

The adoption of powerful diffusion models is hindered by their significant inference latency. Recent ``cache-then-forecast'' schemes alleviate this issue by accelerating DiTs using derivative-based polynomials, but they suffer from severe quality degradation at high acceleration ratios. Our analysis reveals its root cause: the discrete extrapolation performed on representations that are misaligned with the continuous diffusion trajectory and are numerically unstable. Thus, accelerated DiTs suffe

Post-training alignment determines the reasoning and human preference following capabilities of large language models, yet most existing works withhold detailed data construction, filtering rules and training recipes, which hinders community reproducibility and lightweight model optimization. This work presents NebulaExp, a fully transparent, ablation-driven post-training pipeline built on Qwen3-8B-base, covering two orthogonal model branches: general instruct model and complex reasoning-special

Complex multi-agent control tasks remain challenging for traditional rule-based and model-based approaches, motivating the adoption of learning-based methods. However, learning-based methods often struggle with sim-to-real transfer because they rely on accurate dynamics modeling or system identification and learn policies in low-level control spaces that are highly sensitive to dynamics mismatch, making them costly and fragile in complex environments. To address this issue, we propose a sim-to-r

Current VLM evaluations often conflate language priors with genuine spatial reasoning. To address this, we introduce CRISP, a novel structural-diagnostic evaluation paradigm that assesses visual spatial intelligence through consistency, the alignment between implicit perception and explicit reasoning. Unlike traditional black-box QA, CRISP utilizes metric 3D Scene Graphs and an oracle intervention protocol to decouple latent reasoning capabilities from perceptual bottlenecks. This granular diagn

AI safety is evaluated by how reliably a model detects the hazards it is told to find, yet accidents often arise from the hazard no one specified. We show that conditioning a language or vision model on a narrow task suppresses its reporting of co-present, safety-critical signals it can otherwise report, a machine analogue of human inattentional blindness, produced by a different mechanism. Across radiology and driving text scenarios and chest-radiograph vision tasks, the ordinary focused instru

Most Vision-Language-Action (VLA) models build on a Vision-Language Model (VLM) backbone by attaching an action module and optimizing the full policy jointly. This design inherits strong visual and linguistic priors from the VLM, but leaves the action module to learn physical motion almost from scratch. As a result, the policy lacks an explicit motion prior, forcing early optimization to simultaneously discover temporal action dynamics and cross-modal alignment, a challenge further amplified in

AI agents are granted access to tools, APIs, and other infrastructure, making them active principals in those systems. The dominant approach places controls inside the agent's own runtime: system prompts, output filters, and guardrail libraries. Any control in the agent's address space is reachable by inputs that influence it; this generalizes to any AI system with sufficient reach into its own runtime, a class we term escapable AI systems. We identify four properties that an authorization mecha

Sparse Mixture-of-Experts (MoE) architectures have emerged as an increasingly influential paradigm as they offer a strategic balance between parameter scalability and computational efficiency. However, low-resource languages, which suffer from a scarcity of high-quality training data, often have their tokens routed to different experts than those predominantly activated by high-resource inputs, which limits cross-lingual expert sharing. This cross-lingual routing divergence consequently hinders

In this paper, we introduce position graphs, a graph-based reasoning framework based on the formalization of position spaces. This framework utilizes two strict partial orders, representing horizontal and vertical alignment and precedence, to model the relative positions of discrete tokens. Unlike general qualitative spatial calculi, position graphs are constrained by a chain condition and compatibility requirements that focus on rows and columns. We provide a comprehensive theoretical analysis

Sparse Autoencoders (SAEs) have shown promise for analyzing language models, but applying them to vision-language models (VLMs) often yields representations that are difficult to use as controllable cross-modal steering directions. We introduce the Joint Sparse Autoencoder (JSAE), which uses an explicit alignment constraint to jointly factorize sequence-pooled vision and language activations into shared, interpretable image/caption-level features. Applied to LLaVA, JSAE recovers cross-modal feat