arXiv:2604. 21991v2 Announce Type: replace Abstract: Multi-task optimization is a powerful approach for solving a large number of tasks in parallel.
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:2606. 16774v1 Announce Type: new Abstract: Equipping Large Language Model (LLM) agents with effective skills is crucial for solving complex tasks in real-world systems like OpenClaw.
arXiv:2603. 02462v2 Announce Type: replace-cross Abstract: A key challenge in developing unified neural solvers for combinatorial optimization (CO) is the efficient generalization of models from a given set of tasks to new tasks unseen during initial training.
arXiv:2606. 29082v1 Announce Type: cross Abstract: Would experience designing faster GPU kernels also help close in on a long-standing open mathematical conjecture?
arXiv:2509. 24256v2 Announce Type: replace-cross Abstract: The pretrain-transfer paradigm, which underpins the success of large language models (LLMs), has demonstrated the immense power of creating foundation models that learn generalizable representations from vast datasets.
arXiv:2606. 22589v2 Announce Type: replace Abstract: Ever since the advent of foundation models and the pre-training-finetuning paradigm, there have been numerous efforts to merge multiple task-specific experts into a single multi-task model.
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.
arXiv:2607. 17760v1 Announce Type: cross Abstract: Inverse reinforcement learning (IRL) provides a powerful framework for learning from demonstrations.
arXiv:2512. 01113v2 Announce Type: replace-cross Abstract: Algorithmic reasoning -- the ability to perform step-by-step logical inference -- is a synthetic benchmark for evaluating multi-step reasoning abilities, designed for graph neural networks and also for transformer models.
Inverse reinforcement learning (IRL) provides a powerful framework for learning from demonstrations. However, real-world tasks often exhibit substantial natural variations (e.
arXiv:2601. 10560v2 Announce Type: replace-cross Abstract: Multi-agent systems (MAS) coordinate multiple LLM-powered agents through structured workflows, gaining reasoning power but incurring high inference latency from multi-step execution and repeated model invocations.
arXiv:2602. 05547v2 Announce Type: replace-cross Abstract: RL-based post-training with GRPO is widely used to improve large language models on individual reasoning tasks.