arXiv:2604. 26170v2 Announce Type: replace Abstract: Adapting large language models (LLMs) to a targeted task efficiently and effectively remains a fundamental challenge.
arXiv:2606. 24841v1 Announce Type: new Abstract: Prompt-based learning has emerged as a dominant paradigm in natural language processing.
arXiv:2510. 16882v4 Announce Type: replace-cross Abstract: Supervised fine-tuning (SFT) is a commonly used technique to adapt large language models (LLMs) to downstream tasks.
arXiv:2607. 04733v1 Announce Type: cross Abstract: Supervised fine-tuning (SFT) is the standard approach for adapting pretrained language models to downstream domains, yet it often improves target-domain behavior at the cost of degrading pre-existing capabilities.
arXiv:2607. 03453v1 Announce Type: cross Abstract: Inference-time alignment methods, such as Best-of-$N$, offer a flexible alternative to training-based alignment by using reward models to select high-quality responses generated by a reference LLM.
arXiv:2607. 11505v1 Announce Type: cross Abstract: Post-training is essential for refining the domain-specific capabilities of large language models (LLMs), yet existing reward optimization and distribution matching methods tightly couple policy exploration with distribution alignment.
The paper introduces HiDeR, a High Information Density Replay framework for Lifelong Person Re-Identification that replaces discrete sample selection with information compression. It uses a complexity‑aware memory allocation based on intra‑class variance and a metric‑guided condensation objective to preserve essential identity topologies, while a cross‑modality adaptation strategy bridges synthetic and real styles to improve training. Experiments show HiDeR outperforms state‑of‑the‑art methods in knowledge retention and generalization, and reduces cumulative replay cost.
arXiv:2608. 09507v1 Announce Type: cross Abstract: Natural language user preferences provide an interpretable interface for LLM personalization.
arXiv:2510. 05342v2 Announce Type: replace-cross Abstract: Direct Preference Optimization (DPO) has emerged as a simple and effective method for aligning large language models.
arXiv:2608. 11746v1 Announce Type: new Abstract: Modern systems are increasingly expected to transfer across tasks not specified during training.
arXiv:2607. 22676v1 Announce Type: new Abstract: Post-training is a key mechanism for adapting large language models to downstream tasks.
Supervised fine-tuning (SFT) is the standard approach for adapting pretrained language models to downstream domains, yet it often improves target-domain behavior at the cost of degrading pre-existing capabilities. Standard cross-entropy fine-tuning promotes only the observed label token and leaves unconstrained how probability mass is redistributed over other plausible alternatives, potentially distorting the rich local preference structure learned during pretraining.
arXiv:2608. 18339v1 Announce Type: cross Abstract: Vision-language models (VLMs) have demonstrated remarkable zero-shot capabilities yet remain sensitive to real-world distribution shifts during inference.