LoRA, PEFT, instruction tuning and domain adaptation — adapting a pretrained model without paying to train one.
arXiv:2606. 11508v1 Announce Type: new Abstract: Accurate prediction of absorption, distribution, metabolism, and excretion (ADME) properties is critical to drug discovery, but remains challenging because ADME endpoints are noisy, interdependent, and often data-limited.
arXiv:2606. 12106v1 Announce Type: cross Abstract: This paper presents our solution to the 2026 SoccerNet VQA Challenge.
arXiv:2606. 07909v2 Announce Type: replace Abstract: Modern large language model (LLM) agents can use external tools to help users solve complex tasks.
arXiv:2606. 11698v1 Announce Type: cross Abstract: Model watermarking safeguards AI model intellectual property by embedding distinctive knowledge that induces unique behavioral signatures.
Recently, large language models (LLMs) have achieved promising progress in the fields of classical Chinese translation and the generation of classical poetry. However, domain-specific research on precise translation and affective-semantic understanding of classical poetry remains limited.
Domain fine-tuning degrades the safety of large language models: fine-tuned specialists readily comply with harmful prompts framed in domain language. Existing inference-time defenses that mix logits from a safe anchor model require both models to share a vocabulary, which rules them out for the cross-family specialists where safety is most degraded.
Diffusion large language models (dLLMs) offer an efficient alternative to autoregressive models through parallel decoding, yet existing post-training methods largely rely on random masking strategies that overlook intrinsic token dependencies. In this work, we present an empirical analysis of attention in dLLMs and show that tokens attending more strongly to unmasked context exhibit greater generation stability and play a critical role in reasoning.
This paper presents our solution to the 2026 SoccerNet VQA Challenge. We first develop a cost-effective data synthesis pipeline driven by a Vision-Language Model (VLM), which systematically restructures raw domain data into diverse VQA samples, including concise answers and long-form responses.
We propose a multi-agent collaborative framework built upon a lightweight Multimodal Large Language Model (MLLM), specifically designed for social intelligence reasoning. A key feature of our approach is that both the training and inference phases are augmented via knowledge distillation.
arXiv:2606. 10216v1 Announce Type: cross Abstract: Advanced Persistent Threats (APTs) are stealthy, multi-stage cyberattacks whose detection is difficult due to scarce labeled traces, severe class imbalance, and the challenge of generating realistic malicious behavior.
arXiv:2606. 10953v1 Announce Type: new Abstract: Furnished floor plans are fundamental to real estate visualization, interior design, and architectural workflows.
arXiv:2606. 10194v1 Announce Type: cross Abstract: Climate change research increasingly requires AI systems that reason across text, dynamic visual content, and scientific figures, yet existing climate QA benchmarks are small, mostly textual, and cover a narrow range of models.
arXiv:2606. 11033v1 Announce Type: cross Abstract: Recent efforts to extend large language models (LLMs) to speech inputs typically rely on cascaded ASR-LLM pipelines, end-to-end speech-language models, or bridge/distillation-based adaptation.
arXiv:2606. 10279v1 Announce Type: new Abstract: Supervised fine-tuning with synthetic rationale data is widely assumed to improve language model performance on clinical prediction tasks by teaching models not just what to predict but why.
arXiv:2512. 18531v2 Announce Type: replace-cross Abstract: One-dimensional NMR spectroscopy is one of the most widely used techniques for the characterization of organic compounds and natural products.
arXiv:2606. 09932v1 Announce Type: cross Abstract: Supervised Fine-Tuning (SFT) followed by Reinforcement Learning (RL) has become a standard pipeline for Large Language Model (LLM) post-training.
arXiv:2606. 09937v1 Announce Type: cross Abstract: We introduce RKSC (Reasoning-Aware KV Cache Sharing), a training-free inference framework that eliminates two structural redundancies in multi-branch LLM reasoning pipelines.
arXiv:2606. 11106v1 Announce Type: cross Abstract: A global shortage of trained sonographers limits prenatal ultrasound screening in low- and middle-income countries, where over half of pregnant women receive no skilled sonography.
arXiv:2606. 09867v1 Announce Type: cross Abstract: Optimizing register transfer level (RTL) code is of vital importance in hardware design.
arXiv:2606. 10180v1 Announce Type: cross Abstract: We introduce flow control of vision-language-action (VLA) models, a simple and effective way to steer VLA actions in real-time through generic inputs, such as a keyboard.