Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv:2608.23149v1 Announce Type: cross Abstract: The alignment of Large Language Models heavily relies on English-centric high-quality preference data, which often leads to suboptimal performance in...
The paper introduces the Unified Path Planner (UPP), a graph‑search algorithm that balances safety and optimality by adaptively weighting heuristics and using a local inverse‑distance safety field. UPP auto‑tunes its parameters during search, guaranteeing suboptimality bounds while improving obstacle clearance. Evaluation on ten simulated environments shows UPP achieving a 0.94 OptiSafe score—significantly higher than existing methods—while adding only 0.5–1% to path length and maintaining a 100% success rate, with hardware validation on a TurtleBot confirming practical benefits.
arXiv:2608.23375v1 Announce Type: cross Abstract: Gumbel-based inference verification bounds LLM weight exfiltration by only forgiving token choices that plausibly arise from honest GPU nondeterminis...
DIAG is a Diagnostic Iterative Alignment and Generation framework designed to improve data efficiency in aligning large language models for mathematical reasoning. It adaptively reshapes the practice distribution by first diagnosing valid preference-pair yield to calibrate exploration and exploitation, then generating targeted practice from the model’s failure traces. The approach is theoretically framed as a teacher‑mediated approximation to KL‑regularized reweighting, and experiments show that DIAG increases preference-pair yield and reasoning performance under the same training budget.
arXiv:2511.17681v2 Announce Type: replace Abstract: Referring Multi-Object Tracking (RMOT) extends conventional multi-object tracking (MOT) by introducing natural language references for multi-modal...
arXiv:2608.23244v1 Announce Type: cross Abstract: Large language models (LLMs) often produce fluent but incorrect answers with unwarranted confidence. A central limitation is that standard LLMs repre...
Breast ultrasound (BUS) is widely used for breast cancer diagnosis yet remains operator-dependent. While deep learning shows promise, ensuring diagnostic reliability and interpretability is challengin...
Artificial Intelligence (AI) algorithms frequently learn creative and unexpected solutions, surprising even expert researchers who develop and study them. They often astonish practitioners by discover...
Reasoning-Induced Misalignment, where fine-tuning on reasoning data containing no harmful content, including mathematics, code, and problem-solving with chain-of-thought traces can induce harmful beha...
Memory is becoming a default subsystem in deployed LLM agents to provide persistent personalization and continuity. This naturally prompts a question: will memory system introduce new vulnerabilities...
Video generation is progressing beyond isolated clips toward long-form narratives and interactive worlds, requiring models to preserve identities, follow user controls, and remain stable over extended...
Fashion complementary image generation (CIG) aims to create garments that stylistically match a seed item based on user intent, making it a natural multimodal grounding problem where models must inter...
In light-field (LF) imaging systems, dense spatial sampling from a camera array enables powerful post-capture capabilities such as refocusing and depth estimation. However, real-world LF capture is of...
Counterfactual (CF) explanations for time-series classifiers are usually evaluated one example at a time: what minimal edit flips this single window's prediction? We argue that the more informative qu...
Media bias detection relies on definitions and examples that specify what counts as bias, yet these specifications often vary across datasets or remain implicit, even when given the same name. Such va...
Vision-language models (VLMs) can answer spatial questions, yet the mechanisms connecting object grounding to spatial reasoning remain poorly understood. It is underexplored whether spatial reasoning...
Image matching is a core component of applications such as Simultaneous Localization and Mapping (SLAM), Visual Localization, and Structure from Motion (SfM). However, the local image features central...
Floating waste in inland waterways threatens aquatic ecosystems and requires timely monitoring under cluttered, multi-object conditions. Existing aquatic-waste datasets provide limited geographic cove...
We develop a finite-width geometric framework describing how learned feature geometries are organized, transported, and selectively aligned in deep neural networks. Incompatibility among weight-genera...
Referring Expression Segmentation (RES) aims to generate a pixel-level mask for the object specified by a language expression. Recent methods based on multimodal large language models (MLLMs) often re...