Multimodal in-context learning (ICL) is becoming a key capability that allows large vision-language models (LVLMs) to adapt to novel tasks without parameter updates, which expands their usefulness in many real-world applications. However, ICL performance remains unstable even when the in-context demonstrations (ICDs) are well matched, showing that LVLMs still struggle to make full use of the provided context. While existing work mainly focuses on prompt engineering or post-hoc logit calibration, we study the attention mechanisms inside LVLMs to address their inherent limitations. We identify two important weaknesses in their self-attention that hinder effective ICL. To address these weaknesses, we propose Context-Aware Modulated Attention (CAMA), a training-free and plug-and-play method that dynamically adjusts attention logits based on the input in-context sequence. CAMA uses a two-stage modulation process that strengthens attention to semantically important tokens, especially visual ones. Across four LVLMs and seven benchmarks, CAMA consistently outperforms vanilla models and baselines, showing clear effectiveness and generalization. It can also activate the intended benefits of prompt engineering methods and remains robust across different sequence configurations. Therefore, CAMA opens up new directions for improving multimodal reasoning through a deeper understanding of attention dynamics.

CompCert project, the state-of-the-art compiler that achieves the first end-to-end formally verified C compiler, does not support fully verified instruction scheduling. Instead, existing research that works on such topics only implements translation validation. This means they do not have direct formal proof that the scheduling algorithm is correct, but only a posterior validation to check each compiling case. Using such a method, CompCert accepts a valid C program and compiles correctly only when the untrusted scheduler generates a correct result. However, it does not guarantee the complete correctness of the scheduler. It also causes compile-time validation overhead in the view of runtime performance. In this work, we present the first achievement in developing a mechanized library for fully verified instruction scheduling while keeping the proof workload acceptably lightweight. The idea to reduce the proof length is to exploit a simple property that the topological reordering of a topological sorted list is equal to a sequence of swapping adjacent unordered elements. Together with the transitivity of semantic simulation relation, the only burden will become proving the semantic preservation of a transition that only swaps two adjacent independent instructions inside one block. After successfully proving this result, proving the correctness of any new instruction scheduling algorithm only requires proof that it preserved the syntax-level dependence among instructions, instead of reasoning about semantics details every time. We implemented a mechanized library of such methods in the Coq proof assistant based on CompCert’s library as a framework and used the list scheduling algorithm as a case study to show the correctness can be formally proved using our theory. We show that with our method that abstracts away the semantics details, it is flexible to implement any scheduler that reorders instructions with little extra proof burden. Our scheduler in the case study also abstracts away the outside scheduling heuristic as a universal parameter so it is flexible to modify without touching any correctness proof.

This paper studies covert communications between a pair of legitimate transmitter-receiver against a watchful warden over fading channels. There coexist multiple friendly helper nodes who are willing to protect the covert communication from being detected by the warden. An uncoordinated jammer selection scheme is proposed where those helpers whose instantaneous channel gains to the legitimate receiver fall below a pre-established selection threshold will be chosen as jammers radiating jamming signals to defeat the warden. Afterwards, we jointly design the optimal selection threshold and transmission rate for maximizing covert throughput under the premise that the detection error of the warden exceeds a certain level. Numerical results demonstrate that the maximal covert throughput improves significantly as the total number of helpers increases.

In this paper, we study covert communications between a pair of legitimate transmitter-receiver against a watchful warden over slow fading channels. There coexist multiple friendly helper nodes who are willing to protect the covert communication from being detected by the warden. We propose an uncoordinated jammer selection scheme where those helpers whose instantaneous channel gains to the legitimate receiver fall below a pre-established selection threshold will be chosen as jammers radiating jamming signals to defeat the warden. By doing so, the detection accuracy of the warden is expected to be severely degraded while the desired covert communication is rarely affected. We then jointly design the optimal selection threshold and message transmission rate for maximizing covert throughput under the premise that the detection error of the warden exceeds a certain level. Numerical results are presented to validate our theoretical analyses. It is shown that the multi-jammer assisted covert communication outperforms the conventional single-jammer method in terms of covert throughput, and the maximal covert throughput improves significantly as the total number of helpers increases, which demonstrates the validity and superiority of our proposed scheme.