Related papers: Attention Meets Reachability: Structural Equivalen…

Since the early Sixties and Seventies it has been known that the regular and context-free languages are characterized by definability in the monadic second-order theory of certain structures. More recently, these descriptive…

Acoustic-to-Word recognition provides a straightforward solution to end-to-end speech recognition without needing external decoding, language model re-scoring or lexicon. While character-based models offer a natural solution to the…

We present a compositional framework for certifying resource bounds in typed programs. Terms are typed with synthesized bounds drawn from an abstract resource lattice, enabling uniform treatment of time, memory, gas, and domain-specific…

With the adoption of retrieval-augmented generation (RAG), large language models (LLMs) are expected to ground their generation to the retrieved contexts. Yet, this is hindered by position bias of LLMs, failing to evenly attend to all…

Reachability analysis has been a prominent way to provide safety guarantees for neurally controlled autonomous systems, but its direct application to neural perception components is infeasible due to imperfect or intractable perception…

The recently proposed Conformer architecture has shown state-of-the-art performances in Automatic Speech Recognition by combining convolution with attention to model both local and global dependencies. In this paper, we study how to reduce…

Despite strong performance on a variety of tasks, neural sequence models trained with maximum likelihood have been shown to exhibit issues such as length bias and degenerate repetition. We study the related issue of receiving…

Neural network architectures in natural language processing often use attention mechanisms to produce probability distributions over input token representations. Attention has empirically been demonstrated to improve performance in various…

Large Speech Language Models (LSLMs) typically operate at high token rates (tokens/s) to ensure acoustic fidelity, yet this results in sequence lengths that far exceed the underlying semantic content, incurring prohibitive inference costs.…

Counterfactual explanation (CE) is a core technique in explainable artificial intelligence (XAI), widely used to interpret model decisions and suggest actionable alternatives. This work presents a structure-aware and robustness-oriented…

Sequence-level evaluations in autoregressive Large Language Models (LLMs) rely on highly dependent token generation. Establishing tight concentration bounds for these processes remains a challenge due to two fundamental bottlenecks in…

Large Language Models (LLMs) have demonstrated impressive reasoning capabilities, yet their direct application to NP-hard combinatorial problems (CPs) remains underexplored. In this work, we systematically investigate the reasoning…

Graph Neural Networks (GNNs) are widely used as the engine for various graph-related tasks, with their effectiveness in analyzing graph-structured data. However, training robust GNNs often demands abundant labeled data, which is a critical…

Multimodal sarcasm detection, which aims to precisely identify pragmatic incongruities between literal text and nonverbal cues, has gained substantial attention in multimodal understanding. Recent advancements have predominantly relied on…

We propose "Generative Fusion Decoding" (GFD), a novel shallow fusion framework designed to integrate large language models (LLMs) into cross-modal text recognition systems for automatic speech recognition (ASR) and optical character…

Retrieval-Augmented Code Generation (RACG) is a critical technique for enhancing code generation by retrieving relevant information. In this work, we conduct an in-depth analysis of code retrieval by systematically masking specific features…

Self-Consistency improves reasoning reliability through multi-sample aggregation, but incurs substantial inference cost. Adaptive self-consistency methods mitigate this issue by adjusting the sampling budget; however, they rely on…

Large audio-language models (LALMs) generalize across speech, sound, and music, but unified decoders can exhibit a \emph{temporal smoothing bias}: transient acoustic cues may be underutilized in favor of temporally smooth context that is…

Constraint-based causal discovery is brittle in finite-sample regimes because erroneous conditional-independence (CI) decisions can cascade into substantial structural errors. We propose Quantitative Argumentation for Causal Discovery…

3D semantic occupancy prediction is a cornerstone for embodied AI, enabling agents to perceive dense scene geometry and semantics incrementally from monocular video streams. However, current online frameworks face two critical bottlenecks:…