Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv:2604.14251v2 Announce Type: replace Abstract: Monitoring LLM safety at scale requires balancing cost and accuracy: a cheap latent-space probe can screen every input, but hard cases should be es...
arXiv:2411.02771v3 Announce Type: replace-cross Abstract: Doubly robust estimators are widely used for estimating average treatment effects and other linear summaries of regression functions. While c...
arXiv:2411.16478v3 Announce Type: replace Abstract: Measuring distribution drifts is a key task in managing distributed, sensitive data, as it underpins a wide range of federated learning and analyti...
arXiv:2501.10573v2 Announce Type: replace-cross Abstract: We study the geometry of token representations at the prompt level in large language models through the lens of intrinsic dimension. Viewing...
arXiv:2608.20430v1 Announce Type: new Abstract: World Action Models (WAMs) improve planning by incorporating future world evolution into action generation, yet existing methods allocate a fixed imagi...
arXiv:2608.20687v1 Announce Type: new Abstract: 3D Gaussian Splatting has achieved remarkable success in novel view synthesis. However, extracting high-fidelity surfaces directly from 3DGS remains ch...
The paper introduces STAG, a stealthy trojan attack framework targeting Graph Foundation Models (GFMs) that operate on text‑attributed graphs (TAGs). STAG jointly generates graph triggers and soft‑prompt text cues so that both modalities converge to a malicious target class while keeping the trigger subgraph structurally similar to the original and the trigger text readable. Experiments on several TAG datasets and GFMs confirm that STAG achieves high attack success rates while remaining difficult to detect.
arXiv:2607.15218v2 Announce Type: replace Abstract: Large language models (LLMs) increasingly serve as high-level planners for embodied agents, where linguistically benign instructions can become uns...
arXiv:2608.20691v1 Announce Type: new Abstract: Panoramic image generation is increasingly important for immersive applications such as virtual reality, augmented reality, and 3D content creation. Un...
arXiv:2608.20748v1 Announce Type: new Abstract: The Visual Geometry Grounded Transformer (VGGT) enables unified feed-forward 3D reconstruction from multi-view images. However, deploying such a high-p...
arXiv:2604.13687v2 Announce Type: replace-cross Abstract: Glitches frequently contaminate data in gravitational-wave detectors, complicating the observation and analysis of astrophysical signals. Thi...
arXiv:2601.21948v2 Announce Type: replace Abstract: Neural visual decoding is a central problem in brain-computer interface research, aiming to reconstruct human visual perception and to elucidate th...
arXiv:2503. 20546v2 Announce Type: replace-cross Abstract: We consider the problem of estimating the expected causal effect $E[Y|do(X)]$ for a target variable $Y$ when treatment $X$ is set by intervention, focusing on continuous random variables.
The paper introduces Driving with DINO (DwD), a framework that uses Vision Foundation Module (VFM) features to bridge simulation and real-world domains for autonomous driving video generation. It addresses the consistency‑realism dilemma by projecting VFM features onto a principal subspace, dropping high‑frequency texture elements, and applying a Random Channel Tail Drop to preserve structural detail. Additional components— a learnable Spatial Alignment Module and a Causal Temporal Aggregator— enhance control precision, spatial alignment, and temporal stability, reducing motion blur and ensuring realistic, consistent outputs.
arXiv:2608.20610v1 Announce Type: cross Abstract: We study causal inference in interrupted time series designs where a treatment affects every unit simultaneously, so that the contemporaneous control...
The paper introduces Embedded Stroop, a diagnostic test that embeds text prompts directly into images to study interference in multimodal large language models (MLLMs). Using the What-Color-Is-the-Text (WCIT) benchmark, which tests 59 fine‑grained colors in standard, flipped, and masked conditions, the authors evaluate 16 models and find that while exact color accuracy is low (6.3%), models still recognize coarse color families (38.4%) but frequently hallucinate the embedded word instead of the true color (Stroop Hallucination Rate of 21.6%). Masking or flipping the embedded text reduces hallucinations, indicating that semantic legibility can dominate visual color perception in MLLMs.
arXiv:2608.20362v1 Announce Type: cross Abstract: Reinforcement learning with verifiable rewards (RLVR) is a standard recipe for training large language models on mathematical reasoning, where an ans...
arXiv:2608.21300v1 Announce Type: new Abstract: Foundation models for medical image segmentation, like prompt-based MedSAM, generalize well across domains and modalities, often in zero or few-shot se...
arXiv:2608.10725v2 Announce Type: replace Abstract: Large language models (LLMs) often rely on shortcuts rather than systematic reasoning, raising safety concerns in medical applications. Allowing mo...
arXiv:2608.11645v2 Announce Type: replace Abstract: Volumetric video streaming turns privacy into a 3D, multi-view problem. Unlike ordinary video, where sensitive content can often be redacted frame...