arXiv:2402.12118v3 Announce Type: replace-cross Abstract: Data Attribution (DA) is an emerging approach in the field of eXplainable Artificial Intelligence (XAI), aiming to identify influential training datapoints which determine model outputs. It seeks to provide transparency about the model and individual predictions, e.g. for model debugging, identifying data-related causes of suboptimal performance. However, existing DA approaches […]
Robust-R1: Degradation-Aware Reasoning for Robust Visual Understanding
arXiv:2512.17532v1 Announce Type: cross Abstract: Multimodal Large Language Models struggle to maintain reliable performance under extreme real-world visual degradations, which impede their practical robustness. Existing robust MLLMs predominantly rely on implicit training/adaptation that focuses solely on visual encoder generalization, suffering from limited interpretability and isolated optimization. To overcome these limitations, we propose Robust-R1, a novel […]
Lights, Camera, Consistency: A Multistage Pipeline for Character-Stable AI Video Stories
arXiv:2512.16954v1 Announce Type: cross Abstract: Generating long, cohesive video stories with consistent characters is a significant challenge for current text-to-video AI. We introduce a method that approaches video generation in a filmmaker-like manner. Instead of creating a video in one step, our proposed pipeline first uses a large language model to generate a detailed production […]
Bots Don’t Sit Still: A Longitudinal Study of Bot Behaviour Change, Temporal Drift, and Feature-Structure Evolution
arXiv:2512.17067v1 Announce Type: cross Abstract: Social bots are now deeply embedded in online platforms for promotion, persuasion, and manipulation. Most bot-detection systems still treat behavioural features as static, implicitly assuming bots behave stationarily over time. We test that assumption for promotional Twitter bots, analysing change in both individual behavioural signals and the relationships between them. […]
SafeBench-Seq: A Homology-Clustered, CPU-Only Baseline for Protein Hazard Screening with Physicochemical/Composition Features and Cluster-Aware Confidence Intervals
arXiv:2512.17527v1 Announce Type: cross Abstract: Foundation models for protein design raise concrete biosecurity risks, yet the community lacks a simple, reproducible baseline for sequence-level hazard screening that is explicitly evaluated under homology control and runs on commodity CPUs. We introduce SafeBench-Seq, a metadata-only, reproducible benchmark and baseline classifier built entirely from public data (SafeProtein hazards […]
DHP: Discrete Hierarchical Planning for Hierarchical Reinforcement Learning Agents
arXiv:2502.01956v3 Announce Type: replace-cross Abstract: Hierarchical Reinforcement Learning (HRL) agents often struggle with long-horizon visual planning due to their reliance on error-prone distance metrics. We propose Discrete Hierarchical Planning (DHP), a method that replaces continuous distance estimates with discrete reachability checks to evaluate subgoal feasibility. DHP recursively constructs tree-structured plans by decomposing long-term goals into […]
Trust-Region Adaptive Policy Optimization
arXiv:2512.17636v1 Announce Type: cross Abstract: Post-training methods, especially Supervised Fine-Tuning (SFT) and Reinforcement Learning (RL), play an important role in improving large language models’ (LLMs) complex reasoning abilities. However, the dominant two-stage pipeline (SFT then RL) suffers from a key inconsistency: SFT enforces rigid imitation that suppresses exploration and induces forgetting, limiting RL’s potential for […]
Towards Reproducibility in Predictive Process Mining: SPICE — A Deep Learning Library
arXiv:2512.16715v2 Announce Type: replace-cross Abstract: In recent years, Predictive Process Mining (PPM) techniques based on artificial neural networks have evolved as a method for monitoring the future behavior of unfolding business processes and predicting Key Performance Indicators (KPIs). However, many PPM approaches often lack reproducibility, transparency in decision making, usability for incorporating novel datasets and […]
G2L:From Giga-Scale to Cancer-Specific Large-Scale Pathology Foundation Models via Knowledge Distillation
arXiv:2510.11176v2 Announce Type: replace-cross Abstract: Recent studies in pathology foundation models have shown that scaling training data, diversifying cancer types, and increasing model size consistently improve their performance. However, giga-scale foundation models, which are trained on hundreds of thousands of slides covering tens of cancer types and contain billions of parameters, pose significant challenges for […]
Key-Conditioned Orthonormal Transform Gating (K-OTG): Multi-Key Access Control with Hidden-State Scrambling for LoRA-Tuned Models
arXiv:2512.17519v1 Announce Type: cross Abstract: We present a simple, PEFT-compatible mechanism that enforces secret-key access control in instruction-tuned language models. K-OTG trains on a dual-path corpus: authorized examples (prefixed with a role key) learn the task output, while unauthorized examples learn a visible block token. At inference, a pre-lm_head hook applies an orthonormal transform to […]