15 accepted papers
Large Reasoning Models (LRMs) have demonstrated remarkable performance on complex tasks but suffer from high computational costs and latency. While selective thinking strategies improve efficiency by routing easy queries to non-thinking models, existing approaches often incur uncontrollable errors, …
Selecting high-quality candidates from large-scale datasets is critically important in resource-constrained applications such as drug discovery, precision medicine, and the alignment of large language models. While conformal selection methods offer a rigorous solution with False Discovery Rate (FDR)…
Efficiently routing queries to the optimal large language model (LLM) is crucial for optimizing the cost-performance trade-off in multi-model systems. However, most existing routers rely on single-model selection, making them susceptible to misrouting. In this work, we formulate LLM routing as the $…
Conformal prediction (CP) is a powerful framework for uncertainty quantification, generating prediction sets with coverage guarantees. Split conformal prediction relies on labeled data in the calibration procedure. However, the labeled data is often limited in real-world scenarios, leading to unstab
Recent text-to-image (T2I) diffusion and flow-matching models can produce highly realistic images from natural language prompts. In practical scenarios, T2I systems are often run in a "generate--then--select" mode: many seeds are sampled and only a few images are kept for use. However, this pipeline
Knowledge distillation (KD) compresses deep neural networks by transferring task-related knowledge from cumbersome pre-trained teacher models to more compact student models. However, vanilla KD for image super-resolution (SR) networks yields only limited improvements due to the inherent nature of SR…
In offline reinforcement learning, it is necessary to manage out-of-distribution actions to prevent overestimation of value functions. One class of methods, the policy-regularized method, addresses this problem by constraining the target policy to stay close to the behavior policy. Although several…
The ever-increasing fine-tuning cost of large-scale pre-trained models gives rise to the importance of dataset pruning, which aims to reduce dataset size while maintaining task performance. However, existing dataset pruning methods require training on the entire dataset, which is impractical for lar…
In the era of large language models (LLMs), detecting pretraining data has been increasingly important due to concerns about fair evaluation and ethical risks. Current methods differentiate members and non-members by designing scoring functions, like Perplexity and Min-k%. However, the diversity and…
Molecular docking is a fundamental technique in structure-based drug discovery, playing a critical role in predicting the binding poses of protein-ligand complexes. While traditional docking methods are generally reliable, they are often computationally expensive. Recent deep learning (DL) approache…
Knowledge distillation (KD) is a promising yet challenging model compression approach that transmits rich learning representations from robust but resource-demanding teacher models to efficient student models. Previous methods for image super-resolution (SR) are often tailored to specific teacher-st…
Conformal prediction is a popular framework of uncertainty quantification that constructs prediction sets with coverage guarantees. To uphold the exchangeability assumption, many conformal prediction methods necessitate an additional hold-out set for parameter tuning. Yet, the impact of violating th…
Tabular data is widely utilized in a wide range of real-world applications. The challenge of few-shot learning with tabular data stands as a crucial problem in both industry and academia, due to the high cost or even impossibility of annotating additional samples. However, the inherent heterogeneity…
``Distribution shift'' is the primary obstacle to the success of offline reinforcement learning. As a learning policy may take actions beyond the knowledge of the behavior policy (referred to as Out-of-Distribution (OOD) actions), the Q-values of these OOD actions can be easily overestimated. Conseq…
Due to the inability to interact with the environment, offline reinforcement learning (RL) methods face the challenge of estimating the Out-of-Distribution (OOD) points. Existing methods for addressing this issue either control policy to exclude the OOD action or make the $Q$ function pessimistic. H…