LoRA, PEFT, instruction tuning and domain adaptation — adapting a pretrained model without paying to train one.
arXiv:2606. 01552v1 Announce Type: new Abstract: Role-playing agents(RPAs) are widely used to steer large language models(LLMs) toward role-consistent behavior, yet existing benchmarks mainly evaluate surface-level fidelity and offer limited insight into decision making under role-alignment value conflicts.
arXiv:2509. 05367v5 Announce Type: replace-cross Abstract: Large Language Model safety alignment predominantly operates on a binary assumption that requests are either safe or unsafe.
arXiv:2605. 30748v2 Announce Type: replace-cross Abstract: We present Chatterbox-Flash, a zero-shot text-to-speech model obtained by fine-tuning a pretrained autoregressive TTS decoder into a block-diffusion decoder, enabling parallel token generation within each block while retaining block-by-block streaming.
arXiv:2509. 24696v2 Announce Type: replace-cross Abstract: Personalizing large language models (LLMs) to individual user preferences is a critical step beyond generating generically helpful responses.
arXiv:2602. 07883v3 Announce Type: replace Abstract: LLM-powered agentic systems excel at complex long-horizon tasks, but remain constrained by static configurations fixed before execution.
arXiv:2411. 09816v5 Announce Type: replace Abstract: Large neural networks achieve state-of-the-art performance on many tasks, yet their sheer size hinders deployment on resource-constrained devices.
arXiv:2512. 20806v3 Announce Type: replace Abstract: Ensuring the safety of language models (LMs) while maintaining their usefulness remains a critical challenge in AI alignment.
arXiv:2606. 00539v1 Announce Type: new Abstract: Training stability is a key bottleneck in low-precision language model training: efficient low-cost paths can still produce short-lived numerical risks at a small set of operators.
arXiv:2512. 12997v2 Announce Type: replace-cross Abstract: CLIP delivers strong zero-shot classification but remains highly vulnerable to adversarial attacks.
arXiv:2602. 18645v2 Announce Type: replace Abstract: Time series reasoning tasks often start with a natural language question and require targeted analysis of a time series.
arXiv:2606. 00160v1 Announce Type: cross Abstract: Large language models (LLMs) suffer from degraded safety capabilities even when fine-tuned with benign datasets.
arXiv:2601. 11460v2 Announce Type: replace-cross Abstract: Learning structured task representations from human demonstrations is essential for bimanual manipulation, where action ordering, object involvement, and interaction geometry vary significantly across executions.
arXiv:2605. 29183v2 Announce Type: replace-cross Abstract: As machine learning(ML) systems evolve to continual adaptation, each re-training cycle uses compute, annotation, and energy.
arXiv:2604. 09041v2 Announce Type: replace-cross Abstract: AI-based weather forecasting now rivals traditional physics-based ensembles, but state-of-the-art (SOTA) models rely on specialized architectures and massive computational budgets, creating a high barrier to entry.
arXiv:2605. 21422v3 Announce Type: replace Abstract: As LLMs continue to scale up, improving training efficiency heavily relies on effective data utilization.
arXiv:2606. 00756v1 Announce Type: new Abstract: Deploying lightweight Large Language Model (LLM) agents on edge servers can reduce latency and move agentic services closer to users, but resource-constrained edge models often struggle with long-horizon tasks that require persistent memory, subgoal tracking, and reflection.
arXiv:2602. 08689v2 Announce Type: replace Abstract: Diffusion models generate samples through an iterative denoising process guided by a pretrained neural network.
arXiv:2602. 14065v2 Announce Type: replace Abstract: Knowledge-intensive Visual Question Answering (KI-VQA) frequently suffers from severe knowledge conflicts caused by the inherent limitations of open-domain retrieval.
arXiv:2512. 00062v2 Announce Type: replace-cross Abstract: Robotic policy learning for complex real-world manipulation tasks has seen rapid recent progress, enabled in large part by the ability to collect demonstrations through human operation.
arXiv:2506. 13702v4 Announce Type: replace-cross Abstract: Single-trajectory preference optimization methods learn from datasets of ((prompt, response, reward)) tuples, offering a practical alternative to pairwise preference learning by directly leveraging scalar feedback.