Related papers: Differentiable Faithfulness Alignment for Cross-Mo…

Weighted finite automata (WFA) can expressively model functions defined over strings but are inherently linear models. Given the recent successes of nonlinear models in machine learning, it is natural to wonder whether ex-tending WFA to the…

Multi-fidelity Reinforcement Learning (RL) frameworks significantly enhance the efficiency of engineering design by leveraging analysis models with varying levels of accuracy and computational costs. The prevailing methodologies,…

Predicting drug-target affinity is fundamental to virtual screening and lead optimization. However, existing deep models often suffer from representation collapse in stringent cold-start regimes, where the scarcity of labels and domain…

This paper challenges the cross-domain semantic segmentation task, aiming to improve the segmentation accuracy on the unlabeled target domain without incurring additional annotation. Using the pseudo-label-based unsupervised domain…

Transfer learning of diffusion models to smaller target domains is challenging, as naively fine-tuning the model often results in poor generalization. Test-time guidance methods help mitigate this by offering controllable improvements in…

Alignment with human preference is a desired property of large language models (LLMs). Currently, the main alignment approach is based on reinforcement learning from human feedback (RLHF). Despite the effectiveness of RLHF, it is intricate…

We provide a theoretical analysis for end-to-end training Discrete Flow Matching (DFM) generative models. DFM is a promising discrete generative modeling framework that learns the underlying generative dynamics by training a neural network…

Accurate and robust disassembly of stripped binaries is challenging. The root of the difficulty is that high-level structures, such as instruction and function boundaries, are absent in stripped binaries and must be recovered based on…

When a language model agrees with a user's false belief, is it failing to detect the error, or noticing and agreeing anyway? We show the latter. Across twelve open-weight models from five labs, spanning small to frontier scale, the same…

Source-Free Domain Adaptation (SFDA) tackles the problem of adapting a pre-trained source model to an unlabeled target domain without accessing any source data, which is quite suitable for the field of data security. Although recent…

Large language models (LLMs) can translate natural language instructions into executable action plans for robotics, autonomous driving, and other domains. Yet, deploying LLM-driven planning in the physical world demands strict adherence to…

We present causal head gating (CHG), a scalable method for interpreting the functional roles of attention heads in transformer models. CHG learns soft gates over heads and assigns them a causal taxonomy - facilitating, interfering, or…

While transformer models exhibit strong capabilities on linguistic tasks, their complex architectures make them difficult to interpret. Recent work has aimed to reverse engineer transformer models into human-readable representations called…

Detrended fluctuation analysis (DFA) is a scaling analysis method used to quantify long-range power-law correlations in signals. Many physical and biological signals are ``noisy'', heterogeneous and exhibit different types of…

Transformer-based pre-trained models like BERT have achieved great progress on Semantic Sentence Matching. Meanwhile, dependency prior knowledge has also shown general benefits in multiple NLP tasks. However, how to efficiently integrate…

Domain adaptation (DA) enables knowledge transfer from a labeled source domain to an unlabeled target domain by reducing the cross-domain distribution discrepancy. Most prior DA approaches leverage complicated and powerful deep neural…

With the release of new large language models (LLMs) like Llama and Mistral, zero-shot cross-lingual transfer has become increasingly feasible due to their multilingual pretraining and strong generalization capabilities. However, adapting…

Semantic segmentation of histopathology images under class imbalance is typically addressed through frequency-based loss reweighting, which implicitly assumes that rare classes are difficult. However, true difficulty also arises from…

Accurate delay models are important for static and dynamic timing analysis of digital circuits, and mandatory for formal verification. However, F\"ugger et al. [IEEE TC 2016] proved that pure and inertial delays, which are employed for…

Speculative data-parallel algorithms for language recognition have been widely experimented for various types of finite-state automata (FA), deterministic (DFA) and nondeterministic (NFA), often derived from regular expressions (RE). Such…