Home Knowledge Base Learning for Efficient

Learning for Efficient

No mentions found

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

Related Articles from SNS

CLaaS: Continual learning as a service for sample efficient online learning

arXiv:2606.05559v1 Announce Type: new Abstract: Deployed large language model agents must adapt to distribution shift in dynamic environments. Ideally, adaptation can be performed from accumulated agent experiences and retain prior capabilities while transferring to future tasks. However, agent actions and environmental transitions can only be sampled once per scenario, as real-world environments cannot be trivially reset.

arXiv CS 5d ago

RLEASE: Reinforcement Learning Efficient Active Space Engine

arXiv:2606.07879v1 Announce Type: new Abstract: Selecting the active space for multireference electronic-structure calculations is a long-standing bottleneck that often requires expert chemical intuition and costly trial-and-error. We introduce RLEASE (Reinforcement Learning Efficient Active Space Engine), a low-cost method for automatic, geometry-dependent active-space selection. A neural network predicts per-orbital diagnostic scores ($\hat{s}_{1}$) from inexpensive Hartree-Fock orbital...

arXiv Physics 1d ago

Turning Back Without Forgetting: Selective Backward Refinement for Parameter-Efficient Continual Learning

Announce Type: new Abstract: While prompt-based parameter-efficient continual learning mitigates catastrophic forgetting by isolating task-specific prompts, this isolation also limits later tasks from improving earlier ones, leaving backward knowledge transfer underexplored. We address this limitation by proposing Selective bAckward refinement for positive Backward knowledge transfER (SABER), a replay-free framework that enables controlled backward transfer in prompt-based continual...

arXiv CS 8d ago

Turning Back Without Forgetting: Selective Backward Refinement for Parameter-Efficient Continual Learning

Announce Type: replace Abstract: While prompt-based parameter-efficient continual learning mitigates catastrophic forgetting by isolating task-specific prompts, this isolation also limits later tasks from improving earlier ones, leaving backward knowledge transfer underexplored. We address this limitation by proposing Selective bAckward refinement for positive Backward knowledge transfER (SABER), a replay-free framework that enables controlled backward transfer in prompt-based continual...

arXiv CS 1d ago

OLIVE: Online Low-Rank Incremental Learning for Efficient Adaptive Exoskeletons

Announce Type: new Abstract: Wearable exoskeleton systems hold promise for restoring mobility in individuals with physical impairments, yet most existing controllers rely on static gait policies that lack the ability to adapt to dynamic real-world environments or individual user characteristics. We present \olive (\underline{O}nline \underline{L}ow-rank \underline{I}ncremental Learning for Efficient Adapti\underline{ve} Exoskeletons), a parameter-efficient online adaptation framework that...

arXiv CS 5d ago

Implicit Bias and Invariance: How Hopfield Networks Efficiently Learn Graph Orbits

arXiv:2512.14338v3 Announce Type: replace Abstract: Many learning problems involve symmetries, and while invariance can be built into neural architectures, it can also emerge implicitly when training on group-structured data. We study this phenomenon in classical Hopfield networks and show they can infer the full isomorphism class of a graph from a small random sample. Our results reveal that: (i) graph isomorphism classes can be represented within a three-dimensional invariant subspace,...

arXiv CS 5d ago

TailLoR: Protecting Principal Components in Parameter-Efficient Continual Learning

Announce Type: new Abstract: Parameter-efficient finetuning methods based on spectral decomposition have enabled progress in Continual Learning. In this paper we introduce TailLoR, which utilizes the singular bases U and V of the pre-trained weights as a fixed reference frame to learn a low-rank update applied to the singular value matrix. A soft spectral penalty discourages updates aligned with dominant singular directions, reducing interference while routing fine-grained adaptation into...

arXiv CS 5d ago

Language Model Networks: Supervision-Efficient Learning through Dense Communication

arXiv:2505.12741v3 Announce Type: replace Abstract: Language models are increasingly used not only as standalone predictors but also as components in larger inference systems, from test-time scaling to multi-agent collaboration. We study language model networks, where pre-trained language models serve as reusable nodes and intelligence emerges from their topology, communication, and optimization. Existing systems mostly communicate through natural language: easy to deploy, but discrete,...

arXiv CS 8d ago

Efficient Learning of Deep State Space Models via Importance Smoothing

arXiv:2605.21108v2 Announce Type: replace Abstract: Latent state space systems are ubiquitous in statistical modelling, arising naturally when time series are observed through noisy measurements. However, training deep state space models (DSSMs) at scale remains difficult. Two largely distinct strategies have emerged for training DSSMs.

arXiv CS 9d ago

Hot-Start Chinese Language Modeling:Visual Glyphs Accelerate Sample-Efficient Learning

Announce Type: replace Abstract: In this work, we study whether rendering Chinese characters as visual glyph images, rather than discrete token IDs as mainstream LLMs do, providing an inductive bias for character-level language modeling. Our central finding gives a double-edged insight: visual inputs produce a pronounced hot-start effect, more than doubling early-stage accuracy within the first epoch (at 0.4% of total training steps) (12.3% visual inputs vs. 5.8% index-based baseline), yet...

arXiv CS 8d ago