arXiv:2607. 21426v1 Announce Type: new Abstract: Cooperative multi-task semantic communication (CMT-SemCom) improves task execution performance by leveraging shared representations.
Cooperative multi-task semantic communication (CMT-SemCom) improves task execution performance by leveraging shared representations. However, as we demonstrated in [1], cooperative multi-tasking can be either constructive or destructive, depending on the semantic relationships among tasks.
arXiv:2607. 16554v1 Announce Type: cross Abstract: In multi-task learning (MTL) negative transfer is often considered as an optimization artifact, but it can also be viewed as a consequence of limited shared capacity and weak task redundancy.
The paper extends the Cooperative Multi-Task Semantic Communication (CMT‑SemCom) framework to jointly perform heterogeneous classification and regression tasks on the Cityscapes dataset, using an InfoMax principle to handle mixed discrete and continuous semantic variables. It compares the new framework against independent single‑task training, conventional task‑agnostic digital transmission, and single‑encoder multi‑decoder SemCom, and studies how the capacity of the common unit affects joint task performance. Extensive evaluations show that CMT‑SemCom outperforms all benchmarks.
arXiv:2606. 18627v1 Announce Type: new Abstract: Model merging has emerged as a training-free alternative to multi-task learning, aiming to combine multiple task-specific fine-tuned models into a single multi-task model.
The paper extends the Cooperative Multi-Task Semantic Communication (CMT‑SemCom) framework to handle heterogeneous classification and regression tasks on the Cityscapes dataset. By incorporating the InfoMax principle, the system accommodates mixed discrete and continuous semantic variables, and it is benchmarked against single‑task training, task‑agnostic digital transmission, and single‑encoder multi‑decoder SemCom. Experiments show that CMT‑SemCom outperforms all baselines and provide insights into how the common unit capacity affects joint task performance.
arXiv:2509. 16959v5 Announce Type: replace-cross Abstract: When different objectives conflict with each other in multi-task learning, gradients begin to interfere and slow convergence, thereby potentially reducing the final model's performance.
arXiv:2608. 15256v1 Announce Type: new Abstract: Collaborative training in distributed semantic communication (DSC) networks typically relies on decentralized federated learning (DFL).
Mixture-Trained Merging (MTM) is a method for creating unified language models that combine multiple objectives—such as mathematics, code, instruction following, and controllable thinking—into a single parameter set. Instead of sequentially post‑training on each objective, MTM trains each branch on a mixture of objectives, ensuring that the branches remain compatible in weight space and can be merged without degrading performance. The approach iteratively refines merge coefficients using low‑cost evaluations and multi‑objective Bayesian optimization, outperforming naive merging and preserving distinct behaviors across domains.
arXiv:2405. 12775v2 Announce Type: replace-cross Abstract: Discovering the semantics of multimodal utterances is essential for understanding human language and enhancing human-machine interactions.
arXiv:2605. 17361v2 Announce Type: replace-cross Abstract: Multi-agent systems (MAS) powered by large language models (LLMs) have emerged as a powerful paradigm for complex problem solving, where performance critically depends on the underlying inter-agent communication topology.
arXiv:2604. 21991v2 Announce Type: replace Abstract: Multi-task optimization is a powerful approach for solving a large number of tasks in parallel.
arXiv:2507. 12612v4 Announce Type: replace-cross Abstract: Supervised fine-tuning performance for large language models depends strongly on how training budget is distributed across a heterogeneous set of tasks.