This paper develops a policy-learning framework to optimally assign prediction tasks to multiple agents, considering individual agent expertise and capacity constraints, achieving systematic performan…

CORE-MTL proposes a representation-centric framework that uses causal orthogonal representations to disentangle task-relevant structure from nuisance variation in multi-task learning, achieving superi…

This paper proposes a semantic-aware task clustering method for Cooperative multi-task semantic communication (CMT-SemCom) to ensure constructive cooperation and mitigate destructive cooperation and n…

The paper introduces RA-MoE, a novel fine-tuning framework that leverages the internal routing structure of Mixture-of-Experts (MoE) models to improve performance on multilingual downstream tasks by a…

The paper proposes DAG-MoE, a novel sparse Mixture-of-Experts framework that replaces standard weighted-sum aggregation with structural aggregation to enhance model performance and enable multi-step r…

The paper proposes pretraining a Perceiver-style in-context learner on synthetic data to solve Multiple Instance Learning (MIL) tasks efficiently in the low-label regime.

A unified multi-task malware analysis framework based on Mixture of Experts (MoE) architectures is proposed for malware family classification, packed versus unpacked detection, and malware versus beni…

The paper proposes a theoretically grounded adversarial multi-task learning framework (AMTIDIN) that significantly improves joint interference detection, modulation identification, and interference id…

CORTIS is a text-only adaptation framework that fine-tunes spoken language models for task-oriented voice agents using text-form task supervision.

The paper introduces TASTE, an automatic task synthesis method that generates challenging agent benchmarks by evolving tool sequences, demonstrating that existing benchmarks are saturated and that TAS…

This paper proposes PPL-Factory, a data selection framework for efficient fine-tuning of large language models using task-aware and budget-aware perplexity-based scores.

Mind-Omni introduces a unified multi-task framework that models the interplay between brain, vision, and language signals using a discrete diffusion paradigm, achieving state-of-the-art performance ac…

The paper introduces Multi-Response Training (MRT) to combat the 'mode lottery' problem in language model fine-tuning, showing that retaining multiple valid responses significantly improves distributi…

The paper establishes the first theoretical framework for analyzing the learnability of Test-Time Adaptation (TTA) under non-stationary data streams by introducing Recovery Complexity, which quantifie…

The paper introduces StreamSynth, a sequential setting for synthetic data generation, and proposes SynLearner, a framework that enables LLMs to improve synthesis performance by accumulating and transf…

SCOPE introduces a data-free self-play framework that co-evolves a task-generating Challenger and a document-answering Solver, significantly improving open-ended performance on language models without…

A framework called DexCompose is proposed to reuse pretrained dexterous policies for multi-task manipulation with explicit finger-level action ownership.

This paper presents a memory-efficient training stack for Mixture-of-Experts (MoE) models, combining and specializing parallelism techniques for maximal efficiency.