Related papers: Deductive Verification of Weak Memory Programs wit…
Diffusion Language Models (dLLMs) have garnered significant attention for their potential in highly parallel processing. The parallel capabilities of existing dLLMs stem from the assumption of conditional independence at high confidence…
Applying reinforcement learning to improve factual accuracy in knowledge-intensive question answering faces a reward design dilemma. Response-level rewards provide only coarse supervision and cannot distinguish correct from incorrect…
Self-supervised learning has developed rapidly over the last decade and has been applied in many areas of computer vision. Decorrelation-based self-supervised pretraining has shown great promise among non-contrastive algorithms, yielding…
Timing side-channel attacks exploit variations in program execution time to recover sensitive information. Cryptographic implementations are especially vulnerable to these attacks, since even small timing differences in operations such as…
Fully automated verification of large-scale software and hardware systems is arguably the holy grail of formal methods. Large language models (LLMs) have recently demonstrated their potential for enhancing the degree of automation in formal…
Speculative decoding and dynamic sparse attention are two complementary approaches for accelerating long-context LLM inference: the former amortizes target-model execution across multiple verifier queries, while the latter reduces each…
Recent breakthroughs in associative memories suggest that silicon memories are coming closer to human memories, especially for memristive Content Addressable Memories (CAMs) which are capable to read and write in analog values. However, the…
Making threaded programs safe and easy to reason about is one of the chief difficulties in modern programming. This work provides an efficient execution model for SCOOP, a concurrency approach that provides not only data race freedom but…
Deductive verification of concurrent programs under weak memory has thus far been limited to simple programs over a monolithic state space. For scalability, we also require modular techniques with verifiable library abstractions. This paper…
Reasoning-centric video object segmentation is an inherently complex task: the query often refers to dynamics, causality, and temporal interactions, rather than static appearances. Yet existing solutions generally collapse these factors…
With the development of quantum hardware bringing the error-corrected quantum circuits to the near future, the lack of an efficient polynomial-time decoding algorithms for logical circuits presents a critical bottleneck. While quantum…
Error correction in automatic speech recognition (ASR) aims to correct those incorrect words in sentences generated by ASR models. Since recent ASR models usually have low word error rate (WER), to avoid affecting originally correct tokens,…
We propose a conceptual integration of deductive program verification into existing user interfaces for software debugging. This integration is well-represented in the "Debug Adapter Protocol", a widely-used and generic technology to…
Concurrent accesses to databases are typically encapsulated in transactions in order to enable isolation from other concurrent computations and resilience to failures. Modern databases provide transactions with various semantics…
While linear programming (LP) decoding provides more flexibility for finite-length performance analysis than iterative message-passing (IMP) decoding, it is computationally more complex to implement in its original form, due to both the…
Weakly supervised semantic segmentation (WSSS) with image-level labels aims to achieve segmentation tasks without dense annotations. However, attributed to the frequent coupling of co-occurring objects and the limited supervision from…
In many applications, training machine learning models involves using large amounts of human-annotated data. Obtaining precise labels for the data is expensive. Instead, training with weak supervision provides a low-cost alternative. We…
To reduce LLM costs and latency, semantic caching systems must accurately identify when a new prompt matches a cached one. Current methods often rely on simplistic similarity measures, which limit their effectiveness. We introduce…
Formal verification provides the highest assurance of software correctness and security, but its application to large-scale, evolving systems remains a major challenge. While large language models (LLMs) have shown promise in automating…
This paper studies reliability-guaranteed decoding for variable-length stop-feedback (VLSF) codes over correlated noncoherent fading channels. The decoding rule is based on the evolution of the information density associated with a given…