Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv:2608. 13690v1 Announce Type: cross Abstract: Medical image segmentation is still largely treated as a vision-only problem, although clinical interpretation often relies on textual knowledge of anatomy, location, appearance, and surrounding context.
arXiv:2608. 13925v1 Announce Type: cross Abstract: Diffusion large language models (dLLMs) accelerate language generation by predicting multiple masks in a single forward pass.
arXiv:2608. 14011v1 Announce Type: cross Abstract: Generative recommendation autoregressively generates the semantic IDs of the target item, unifying preference modeling and index retrieval within the shared token space.
arXiv:2608. 13651v1 Announce Type: cross Abstract: We solve exactly a fundamental problem of adaptive control against adversarial disturbances: regulate the scalar system $x_{t+1} = ax_t + u_t + w_t$, $x_0=0$, $\|w\|_\infty \le 1$, where the constant pole $a \in [-\Delta, \Delta]$ is unknown in sign and magnitude and $\Delta$ is arbitrarily large.
arXiv:2608. 14286v1 Announce Type: cross Abstract: Vision language models (VLMs) are increasingly used in industrial decision-making systems, such as recruitment support and recommendation.
arXiv:2602. 23459v2 Announce Type: replace Abstract: Psychiatric questionnaires are highly context sensitive and often only weakly predict subsequent symptom severity, which makes the prognostic relationship difficult to learn.
arXiv:2605. 30556v2 Announce Type: replace Abstract: CORRECTION (August 2026): the central finding of this paper is not supported.
arXiv:2608. 13695v1 Announce Type: cross Abstract: Large language model providers routinely cite multilingual safety benchmarks spanning a dozen or more languages as evidence that their models are safe for non-English-speaking users.
arXiv:2608. 14089v1 Announce Type: new Abstract: Safety classifiers deployed with large language models often fail for two reasons: their decisions reflect the policy learned during training rather than the deployer's desired policy, and their performance degrades as deployment traffic evolves.
Camera-based object detectors are vulnerable to physical adversarial attacks designed to suppress detections. While adversarial training and input purification offer some protection, they often overfit to specific attack distributions and fail on adaptive adversaries.
Text-driven human motion editing aims to modify existing motion sequences according to natural language instructions while maintaining the structural consistency of the original motion. Existing diffusion-based approaches struggle to balance text-responsive "change" and inertial "invariance".
Friday's big release was Qwen 3. 8 27B , an Apache 2 licensed 27B parameter vision-capable LLM from Alibaba's Qwen research lab.
As state-of-the-art machine translation models saturate standard benchmarks, the field needs more challenging evaluations to distinguish between models of varying quality. We propose augmenting existi...
Visual document retrieval is a critical component of multimodal retrieval-augmented generation, aiming to identify query-relevant pages from document collections where evidence is distributed across t...
The rapid development and widespread application of artificial intelligence (AI) have sparked intense discussions on how to deploy responsible AI systems in a manner aligned with human values and ethi...
\textit{Split Federated Learning} (SFL) enables distributed model training by splitting networks between the server and clients. However, under client heterogeneity, the conventional static split stra...
Large language model (LLM)-assisted energy-management tools can translate natural-language context into structured grid commands, but syntactic validity does not imply physical admissibility. This pap...
Bangla-English tutoring requires more than producing a correct translation: learners also need explanations of grammar differences, awareness of their likely errors, and targeted practice. We present...
We investigate whether Mixture-of-Experts (MoE) language models develop linguistically structured expert routing during bilingual language acquisition. Inspired by the Declarative-Procedural framework...
Can a language model do live adversarial level design? Yes, emphasis on the adversarial part The post I Made an LLM Lay Siege to My Minecraft House appeared first on Towards Data Science .