Related papers: Deductive Verification of Weak Memory Programs wit…

VeriFast is one of the leading tools for semi-automated modular formal program verification. A central feature of VeriFast is its support for higher-order ghost code, which enables its support for expressively specifying fine-grained…

Large Language Models (LLMs) have recently achieved strong performance in software code generation. However, applying them to hardware description languages (HDLs), such as Verilog, remains challenging because high-quality training data are…

Several recent deep learning (DL) based techniques perform considerably well on image-based multilingual text detection. However, their performance relies heavily on the availability and quality of training data. There are numerous types of…

The large size of the KV cache has become a major bottleneck for serving LLMs with increasing context lengths. In response, many KV cache compression methods, such as token dropping and quantization, have been proposed. However, almost all…

Error correction is widely used in automatic speech recognition (ASR) to post-process the generated sentence, and can further reduce the word error rate (WER). Although multiple candidates are generated by an ASR system through beam search,…

Hardware enclaves rely on a disjoint memory model, which maps each physical address to an enclave to achieve strong memory isolation. However, this severely limits the performance and programmability of enclave programs. While some prior…

Continual memory augmentation lets computer-using agents (CUAs) learn from prior interactions, but unvetted memories can encode domain-inappropriate or unsafe heuristics--spurious rules that drift from user intent and safety constraints. We…

Visual autoregressive (AR) generation models have demonstrated strong potential for image generation, yet their next-token-prediction paradigm introduces considerable inference latency. Although speculative decoding (SD) has been proven…

Current multimodal models often suffer from shallow reasoning, leading to errors caused by incomplete or inconsistent thought processes. To address this limitation, we propose Self-Verification and Self-Rectification (SVSR), a unified…

The last decade has sparked several valiant efforts in deductive verification of distributed agreement protocols such as consensus and leader election. Oddly, there have been far fewer verification efforts that go beyond the core protocols…

To provide safety guarantees for learning-based control systems, recent work has developed formal verification methods to apply after training ends. However, if the trained policy does not meet the specifications, or there is conservatism…

Disentanglement is a runtime property of parallel programs guaranteeing that parallel tasks remain oblivious to each other's allocations. As demonstrated in the MaPLe compiler and run-time system, disentanglement can be exploited for fast…

The recent development of deep learning methods provides a new approach to optimize the belief propagation (BP) decoding of linear codes. However, the limitation of existing works is that the scale of neural networks increases rapidly with…

Referring Camouflaged Object Detection (Ref-COD) focuses on segmenting specific camouflaged targets in a query image using category-aligned references. Despite recent advances, existing methods struggle with reference-target semantic…

A memory consistency model specifies the allowed behaviors of shared memory concurrent programs. At the language level, these models are known to have a non-trivial impact on the safety of program optimizations, limiting the ability to…

We propose a reduced complexity approach to pattern-based soft decoding of block codes. We start from the ORDEPT decoding algorithm which tests a list of partial error patterns organized in the order of their likelihood and attempts to…

This paper proposes a technique to specify and verify whether a loop can be parallelised. Our approach can be used as an additional step in a parallelising compiler to verify user annotations about loop dependences. Essentially, our…

Speculative decoding accelerates autoregressive language model inference by verifying multiple draft tokens in parallel. However, the verification stage often becomes the dominant computational bottleneck, especially for long-context inputs…

Image forgery localization aims to precisely identify tampered regions within images, but it commonly depends on costly pixel-level annotations. To alleviate this annotation burden, weakly supervised image forgery localization (WSIFL) has…

Reinforcement Learning from Verifiable Rewards (RLVR) has improved language models in domains such as mathematics and code, where correctness can be checked automatically. However, many important tasks are only partially verifiable: prompts…