collaborators

24 papers

cs.CV2026

Detecting AI-Generated Video: A Vision-Language Dual-View Survey

Dylan Xinming Hou, Juntian Zhang, Xu Gu +5

The evolving realism of AI-generated Videos (AIGC-V) is rapidly rendering traditional artifact-centric detection insufficient, necessitating a paradigm shift from low-level inspect…

cs.CR2026

SPQR: A Multi-Dimensional Benchmark for Safety Alignment under Benign Model Adaptation

Mohammed Talha Alam, Nada Saadi, Fahad Shamshad +4

Text-to-image diffusion models can emit copyrighted, unsafe, or private content. Safety alignment aims to suppress specific concepts, yet evaluations seldom test whether safety per…

cs.LG2026

Entropy-Gated Latent Recursion

Soham Bhattacharjee, Dushyant Singh Chauhan, Salem Lahlou +2

Inference-time scaling has become the dominant lever for improving language-model reasoning, but existing methods derive rollout diversity from a single source: stochastic token-le…

cs.LG2026

A Gravitational Interpretation of Fine-Tuning Reversion

Samuele Poppi, Nils Lukas

Fine-tuning on harmless data can partially undo behaviors acquired earlier in training. Safety can erode under benign post-alignment updates, unlearned capabilities can re-emerge,…

cs.DC2026

PreLort: Prefix-Nested LoRA for Federated Fine-Tuning under Rank Heterogeneity

Muhammad Waseem, Nurbek Tastan, Andrej Jovanovic +4

Federated fine-tuning of large language models using parameter-efficient methods such as LoRA enables privacy-preserving adaptation of foundation models. Heterogeneous hardware res…

cs.AI2026

When the Chain of Thought Knows Better: Failure Modes in Multi-Turn Reasoning Models

Sai Kartheek Reddy Kasu, Nils Lukas, Samuele Poppi

Failures in multi-turn reasoning models are largely invisible to terminal-score evaluation. A model can lock onto an unsafe stance early in a long dialogue, yet its final-turn refu…