DETR-style detectors use one-to-one bipartite matching during training to assign object queries to ground-truth objects, enabling end-to-end set prediction without non-maximum suppression (NMS). However, without an explicit de-duplication procedure, multiple queries can still produce highly similar hypotheses for the s …
Visual-token compression improves the efficiency of large vision-language models, but can expose failures that full-token evaluation misses. We study adversarial images that preserve full-token correctness yet induce errors after compression, even when both inference paths succeed on the clean image. Creating such fail …
Uncontrolled repetition can prolong autoregressive generation in large language models (LLMs) and enable resource consumption attacks. Prior analyses of repetitive generation have identified strongly activated features in intermediate and late layers. However, how uncontrolled repetition activity emerges and develops b …
Large reasoning models (LRMs) improve performance on complex tasks through extended reasoning, yet the same process can degenerate into redundant verification and persistent generation loops. Such uncontrolled reasoning increases inference cost and creates risks of resource exhaustion and service degradation. However, …
Large language models (LLMs) exhibit strong general capabilities that mechanistic interpretability has attributed to sparse computational circuits. However, existing circuit studies emphasize preserving functionality or explaining safety, leaving the mechanisms underlying failures across a broader range of tasks largel …
Visual token compression reduces the inference cost of Large Vision-Language Models (LVLMs). However, aggregate robustness measures do not reveal whether a particular adversarial failure is induced by compression or inherited from the underlying model. We define a compression-specific failure (CSF) as an adversarial in …
Agent skills package instructions, executable code, and task-specific resources into reusable artifacts that agents can improve using execution feedback. The same mechanism also enables attackers to evolve malicious skills, making them more effective and less detectable. However, a candidate skill may pass pre-executio …