Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
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...
arXiv:2611.06247v1 Announce Type: new Abstract: Cross-modal remote sensing image retrieval (RS-CMIR) requires representations that are simultaneously modality-invariant and semantically discriminativ...
arXiv:2611.06302v1 Announce Type: new Abstract: Fine-grained action understanding requires vision-language models to ground what an agent does, how it acts, and why it acts in spatio-temporal evidenc...
arXiv:2611.06635v1 Announce Type: new Abstract: Unmanned aerial vehicle (UAV)-based collaborative perception enables multiple agents to share complementary perceptual information, overcoming limitati...
arXiv:2611.06796v1 Announce Type: new Abstract: Few-step distillation offers efficient generation with diffusion and flow models, but preserving quality with only a few sampling steps remains challen...
arXiv:2611.06890v1 Announce Type: new Abstract: For many computer vision tasks, neural networks can be trained to produce a low average error, yet they still fail on seemingly simple scenes. Reducing...
arXiv:2606.18439v2 Announce Type: replace Abstract: Visual Geometry Grounded Transformer (VGGT) recovers dense 3D scene structure from multi-view images in one forward pass, but quadratic cross-frame...
arXiv:2608.12088v2 Announce Type: replace Abstract: Generative models can produce images nearly indistinguishable from real data, yet rigorous and interpretable evaluation remains challenging. Conven...
arXiv:2611.03114v2 Announce Type: replace Abstract: 3D Gaussian Splatting (3DGS) has become a vital tool in novel view synthesis. 3D Gaussian functions with attributes like color, opacity, and scale...
EmoReward is a self‑evolving reward calibration framework for emotional video generation using reinforcement learning. It distills reliability from reward traces during training to adaptively weight multiple reward primitives—such as visual quality, motion, and text alignment—based on emotional evidence. The method employs grounding cues, heterogeneous signal primitives, reflective reward gating, and a RewardMemory module to calibrate fusion weights across training runs, demonstrating improvements on HunyuanVideo 1.5 and transferability to SD 3.5 and FLUX.
The paper investigates end‑to‑end FP4 reinforcement learning for Mixture‑of‑Experts large language models and finds that existing recovery techniques for dense models fail to improve accuracy in the MoE setting. The authors attribute this to the discrete routing decisions in MoE, which make training‑inference policy alignment highly sensitive to asymmetry in recovery methods. They introduce MoEResQ, a symmetric quantization‑recovery recipe that restores alignment and significantly narrows the accuracy gap to full precision.
The study empirically investigates how length‑normalized Direct Preference Optimization (DPO) with a Structured Fine‑Tuning (SFT) retention term (RPO objective) affects downstream capabilities of a Qwen3.5‑4B model fine‑tuned with sparse LoRA on structured financial‑filing tasks. Results show that the alignment tax is graded and task‑selective: extraction performance is largely preserved, JSON extraction degrades modestly, and router‑based tasks suffer severe loss, with most degradation attributed to suppression of rejected completions. The analysis uses 8 seeds, artifact‑aware scoring, and TOST equivalence testing to quantify these effects across different reward margins and precision settings.
CARTBench is a new benchmark for evaluating large language model shopping assistants on complex, ambiguous requests that involve timelines. It compiles 1,603 timestamped dialogues from 17 retail domains and pairs them with product records, then uses case‑specific rubrics based on Ideal Response Principles to score responses across Core, Excellence, and Safety criteria. In a full‑suite evaluation of ten commercial APIs and several open‑weight models, only three models scored above 90% on Core and none surpassed 45% on Excellence, revealing a gap between required behavior and high‑quality purchase advice.
LITMUS is a benchmark for testing the safety of large language model agents in real operating system environments, focusing on behavior jailbreaks that can cause irreversible OS-level harm. It includes 819 high-risk test cases organized into a harmful seed subset and six attack-extended subsets covering jailbreak speaking, skill injection, and entity wrapping, and employs a semantic-physical dual verification mechanism with OS-level state rollback. Evaluation of frontier agents shows that even strong models can execute dangerous operations, exhibit execution hallucination, and are vulnerable to skill injection and entity wrapping attacks.