Related papers: Verifier-Guided Code Translation via Meta-Step Dec…
In this paper, a streaming transmission setup is considered where an encoder observes a new message in the beginning of each block and a decoder sequentially decodes each message after a delay of $T$ blocks. In this streaming setup, the…
Code pre-trained models (CodePTMs) have recently demonstrated significant success in code intelligence. To interpret these models, some probing methods have been applied. However, these methods fail to consider the inherent characteristics…
\textbf{VeriTrans} is a reliability-first ML system that compiles natural-language requirements into solver-ready logic with validator-gated reliability. The pipeline integrates an instruction-tuned NL$\!\to\!$PL translator, round-trip…
Multi-modal large language models (MLLMs) have achieved remarkable capabilities by integrating visual perception with language understanding, enabling applications such as image-grounded dialogue, visual question answering, and scientific…
Large language models (LM) based on Transformers allow to generate plausible long texts. In this paper, we explore how this generation can be further controlled at decoding time to satisfy certain constraints (e.g. being non-toxic,…
The ability to adapt to unseen, local contexts is an important challenge that successful models of source code must overcome. One of the most popular approaches for the adaptation of such models is dynamic evaluation. With dynamic…
Large language models (LLMs) struggle with multi-step reasoning, where inference-time scaling has emerged as a promising strategy for performance improvement. Verifier-guided search outperforms repeated sampling when sample size is limited…
As one of the key tools in many security tasks, decompilers reconstruct human-readable source code from binaries. Yet, despite recent advances, their outputs often suffer from syntactic and semantic errors and remain difficult to read.…
Conventional turbo codes (CTCs) usually employ a block-oriented interleaving so that each block is separately encoded and decoded. As interleaving and de-interleaving are performed within a block, the message-passing process associated with…
Gradually-typed programming languages permit the incremental addition of static types to untyped programs. To remain sound, languages insert run-time checks at the boundaries between typed and untyped code. Unfortunately, performance…
Large Language Models (LLMs) have achieved remarkable success in automated code translation. While prior work has focused on improving translation accuracy through advanced prompting and iterative repair, the reliability of the underlying…
Scheduled sampling is widely used to mitigate the exposure bias problem for neural machine translation. Its core motivation is to simulate the inference scene during training by replacing ground-truth tokens with predicted tokens, thus…
Large Reasoning Models (LRMs) achieve remarkable inference-time improvements through parallel thinking. However, existing methods rely on redundant sampling of reasoning trajectories, failing to effectively explore the reasoning space to…
Speculative decoding has emerged as an effective approach for accelerating autoregressive inference by parallelizing token generation through a draft-then-verify paradigm. However, existing methods rely on static drafting lengths and rigid…
Unified decoder-only transformers have shown promise for multimodal generation, yet the mechanisms by which they synchronize modalities with heterogeneous sampling rates remain underexplored. We investigate these mechanisms through…
Verifiers can improve language model capabilities by scoring and ranking responses from generated candidates. Currently, high-quality verifiers are either unscalable (e.g., humans) or limited in utility (e.g., tools like Lean). While LM…
A common and effective way to train translation systems between related languages is to consider sub-word level basic units. However, this increases the length of the sentences resulting in increased decoding time. The increase in length is…
Temporal Sentence Grounding in Videos (TSGV), which aims to ground a natural language sentence in an untrimmed video, has drawn widespread attention over the past few years. However, recent studies have found that current benchmark datasets…
Dirty paper coding (DPC) refers to methods for pre-subtraction of known interference at the transmitter of a multiuser communication system. There are numerous applications for DPC, including coding for broadcast channels. Recently,…
Software version migration and program translation are an important and costly part of the lifecycle of large codebases. Traditional machine translation relies on parallel corpora for supervised translation, which is not feasible for…