Fluent Alignment with Disfluent Judges: Post-training for Lower-resource Languages
arXiv:2512.08777v1 Announce Type: cross Abstract: We propose a post-training method for lower-resource languages that preserves fluency of language models even…
Refining Visual Artifacts in Diffusion Models via Explainable AI-based Flaw Activation Maps
arXiv:2512.08774v1 Announce Type: cross Abstract: Diffusion models have achieved remarkable success in image synthesis. However, addressing artifacts and unrealistic regions…
Artificial Intelligence-Driven Network-on-Chip Design Space Exploration: Neural Network Architectures for Design
arXiv:2512.07877v1 Announce Type: cross Abstract: Network-on-Chip (NoC) design requires exploring a high-dimensional configuration space to satisfy stringent throughput requirements and…
Impact of Data-Oriented and Object-Oriented Design on Performance and Cache Utilization with Artificial Intelligence Algorithms in Multi-Threaded CPUs
arXiv:2512.07841v1 Announce Type: new Abstract: The growing performance gap between multi-core CPUs and main memory necessitates hardware-aware software design paradigms.…
TV2TV: A Unified Framework for Interleaved Language and Video Generation
arXiv:2512.05103v2 Announce Type: replace-cross Abstract: Video generation models are rapidly advancing, but can still struggle with complex video outputs that…
ESPADA: Execution Speedup via Semantics Aware Demonstration Data Downsampling for Imitation Learning
arXiv:2512.07371v1 Announce Type: cross Abstract: Behavior-cloning based visuomotor policies enable precise manipulation but often inherit the slow, cautious tempo of…
Asymptotic analysis of shallow and deep forgetting in replay with Neural Collapse
arXiv:2512.07400v1 Announce Type: cross Abstract: A persistent paradox in continual learning (CL) is that neural networks often retain linearly separable…
Simulating Life Paths with Digital Twins: AI-Generated Future Selves Influence Decision-Making and Expand Human Choice
arXiv:2512.05397v2 Announce Type: replace-cross Abstract: Major life transitions demand high-stakes decisions, yet people often struggle to imagine how their future…
Going All-In on LLM Accuracy: Fake Prediction Markets, Real Confidence Signals
arXiv:2512.05998v1 Announce Type: new Abstract: Large language models are increasingly used to evaluate other models, yet these judgments typically lack…
Dynamic Correction of Erroneous State Estimates via Diffusion Bayesian Exploration
arXiv:2512.03102v2 Announce Type: replace-cross Abstract: In emergency response and other high-stakes societal applications, early-stage state estimates critically shape downstream outcomes.…