Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv:2512.20773v5 Announce Type: replace Abstract: Realistic user simulation is crucial for training and evaluating multi-turn dialogue systems, yet creating simulators that accurately replicate hum...
arXiv:2601.20476v3 Announce Type: replace Abstract: We investigate how provision of in-context examples based on discourse similarity affects quality and hallucination in diagram code generation from...
arXiv:2602.09870v3 Announce Type: replace Abstract: Steering methods influence Large Language Model behavior by identifying semantic directions in hidden representations, but are typically realized t...
arXiv:2603.01865v4 Announce Type: replace Abstract: LLM-as-judge evaluation has become standard practice for open-ended model assessment; however, judges exhibit systematic biases that cannot be aver...
arXiv:2603.19002v2 Announce Type: replace Abstract: Simulating survey responses with LLMs offers a scalable alternative to costly human data collection, yet evaluation methods remain ad hoc and incon...
arXiv:2604.08567v3 Announce Type: replace Abstract: Large language models (LLMs) and LLM-based agents are increasingly deployed as assistants in planning and decision making, yet most existing system...
arXiv:2606.19544v2 Announce Type: replace Abstract: LLM-as-a-Judge has become the dominant evaluation paradigm for language models, but judge validation in practice relies on exact-match agreement, a...
arXiv:2611.04878v2 Announce Type: replace Abstract: Despite their remarkable capabilities, large foundation models (LFMs) remain susceptible to adversarial manipulation. Current safety intervention m...
arXiv:2611.05380v1 Announce Type: new Abstract: Visual autoregressive generation spans two dominant paradigms: next-scale prediction for images and video, and next-frame prediction for video. Both de...
arXiv:2611.05404v1 Announce Type: new Abstract: The hand localization problem has been a longstanding focus due to its many applications. The task involves modeling the hand as a singular point and d...
arXiv:2611.05599v1 Announce Type: new Abstract: Grounding a text query in an image needs a matrix scoring every term against every patch. Vision-language models compute it with an aligned text encode...
arXiv:2611.05648v1 Announce Type: new Abstract: Adversarial diffusion distillation has conventionally relied on image features for discrimination. We revisit this choice for multimodal diffusion tran...
arXiv:2611.05818v1 Announce Type: new Abstract: Marine surface vehicles (MSVs) have attracted considerable attention for their commercial, scientific, and military applications. Owing to their favora...
arXiv:2611.05893v1 Announce Type: new Abstract: Identity-preserving video generation aims to synthesize high-quality and visually realistic videos from textual and visual conditions while faithfully...
arXiv:2611.05969v1 Announce Type: new Abstract: Single Image Reflection Removal (SIRR) seeks to recover the transmitted scene from a photograph captured through glass. Recent latent restoration metho...
arXiv:2611.06020v1 Announce Type: new Abstract: A 3D Gaussian Splatting (3DGS) reconstruction inherits arbitrary units from structure-from-motion, so it cannot be measured or used to place AR content...
arXiv:2611.06047v1 Announce Type: new Abstract: Large vision-language models (LVLMs) have recently been extended to handle multiple input images, but this extension dramatically increases the visual...
arXiv:2611.06083v1 Announce Type: new Abstract: Omni models answer questions about videos by jointly processing sampled frames and audio in one turn, with progress driven largely by scaling model siz...
arXiv:2611.06143v1 Announce Type: new Abstract: Segment Anything Model 3 (SAM 3) can segment objects from text prompts and track them across video, but its memory and computation costs make deploymen...
arXiv:2611.06203v1 Announce Type: new Abstract: We estimate the quality of a specific target region (e.g., a train body) in an image, rather than the whole image. This differs fundamentally from whol...