Home Knowledge Base Multi-Domain Learning

Multi-Domain Learning

No mentions found

This entity hasn't been tracked yet, or Iris is still building its knowledge base.

Related Articles from SNS

Scaling Datasets for Multi-Sensor, Multi-Agent, and Multi-Domain Learning in Autonomous Systems

Announce Type: cross Abstract: Existing datasets cannot support large-scale learning in multi-agent, multi-sensor, or multi-domain autonomy, where diversity and coordination are essential. We present a modular dataset generation pipeline that creates terabyte-scale, ground-truth-labeled data for ground, aerial, and infrastructure-based systems using the AVstack framework and CARLA simulator. Supporting single- and multi-agent configurations with flexible sensor suites, the pipeline enables...

arXiv CS 6d ago

A Local Perturbation Theory for Cross-Domain Interference and Recovery in Multi-Domain RL

arXiv:2606.02398v1 Announce Type: new Abstract: Reinforcement learning (RL) post-training improves large language models (LLMs) on individual domains such as mathematical reasoning, code generation, question answering, and creative writing (CW), but training on one domain often degrades performance on others. Existing explanations based on catastrophic forgetting or global gradient conflict are incomplete: substantial interference can occur even when full-model gradients are nearly...

arXiv CS 8d ago

Aletheia: What Makes RLVR For Code Verifiers Tick?

arXiv:2601.12186v3 Announce Type: replace Abstract: Multi-domain thinking verifiers trained via Reinforcement Learning with Verifiable Rewards (RLVR) are a cornerstone of modern post-training. However, their adoption in code generation has lagged behind that of execution feedback due to the prohibitive costs of the full RLVR pipeline. In this work, we ablate three primary choices along the performance-cost trade-off in RLVR: intermediate thinking traces, learning from negative samples, and...

arXiv CS 7d ago

USAD 2.0: Scaling Representation Distillation for Universal Audio Understanding

arXiv:2606.06444v1 Announce Type: cross Abstract: Audio encoders are critical to modern audio applications as large language models (LLMs) increasingly rely on a single encoder for diverse inputs. While self-supervised learning (SSL) has yielded strong domain-specific encoders like speech or music experts, multi-domain approaches like USAD and SPEAR remain limited in coverage and evaluation. Recent studies also suggest supervised encoders align better with audio LLMs.

arXiv CS 5d ago

DEER: Disentangled Mixture of Experts with Instance-Adaptive Routing for Generalizable Machine-Generated Text Detection

arXiv:2511.01192v2 Announce Type: replace Abstract: Detecting machine-generated text has become a critical challenge amid the rapid advancement of LLMs, yet existing detectors degrade severely under domain shift. Through systematic pilot studies, we trace this vulnerability to two fundamental flaws in current generalization strategies, namely the incomplete preservation of domain-specific knowledge during multi-domain training and the misalignment between knowledge retrieval and the...

arXiv CS 6d ago

Explaining Data Mixing Scaling Laws

arXiv:2606.08167v1 Announce Type: new Abstract: Recent research has established empirical scaling laws to predict model performance on multi-domain data mixtures. However, a theoretical understanding of these model loss behaviors remains absent. In this work, we propose a unified framework to explain the underlying mechanics of data mixing.

arXiv CS 1d ago

Physics-Informed Neural Networks for Radial Consolidation of Combined Electroosmotic, Vacuum and Surcharge Preloading Considering Smear Effects

arXiv:2606.00056v1 Announce Type: cross Abstract: This study develops a dimensionless multi-domain physics-informed neural network (PINN) framework for electro-osmotic radial consolidation considering smear effects and combined vacuum and surcharge loading. Three PINN-based models are investigated: a standard soft-constrained PINN (Std-PINN), a modified gated PINN (Mod-PINN), and a modified gated PINN with hard-constraint boundary encoding (Mod-HC-PINN). The models are evaluated against FEM...

arXiv Physics 8d ago

The Unreasonable Redundancy of Nature's Protein Folds

The Unreasonable Redundancy of Nature's Protein Folds Over the last few years, deep neural networks have made generative language modeling dramatically more powerful, giving us large language models. A similar leap happened for continuous modalities like images and videos.

Hacker News 7d ago

Armed forces prepared for both short and intense conflicts: Army chief Gen Dwivedi

In an interview with TOI’s Surendra Singh, Chief of Army Staff General Upendra Dwivedi, who has been leading the 12.4 lakh-strong Indian Army since June 30, 2024 and played a key role in rolling out Operation Sindoor, spoke at length about how lessons learnt from last year's operation against Pakistan are now part of the Army doctrine; how drones are now central to India’s battlefield operations; the changing warfare tactics and technologies; and why Pakistan must deter from another terror...

Times of India 5d ago

A year after India broke Pak's offensive during Op Sindoor, Joint Air Defence Doctrine release

On the eve of his retirement, Chief of Defence Staff General Anil Chauhan unveiled the Joint Air Defence Doctrine, a step towards integrating the Army, Navy and Air Force into a seamless, multi-layered shield against aerial threats. The doctrine, released by Headquarters Integrated Defence Staff (IDS), is designed to strengthen operational preparedness and ensure synergy across the services in an era of drones, hypersonic weapons and saturation missile attacks. This is the 13th doctrine...

Times of India 11d ago