small language model

Harness-Driven Progressive Detail: Making Stateless and Small Language Models Do Bounded Agentic Work — An Implementation Report under PSOS and LMCP

Agentic coding and operations work is usually delegated to a model running an open tool loop: the model decides each next step, re-reads its growing transcript every turn, and stops when it believes it has finished. That arrangement is affordable on a provider with prompt caching, where each turn pays only for new toke...

Building AI Systems That Work Offline: An Offline-First Architecture and Feasibility Assessment for Low-Connectivity Environments

Artificial intelligence applications increasingly rely on continuous cloud connectivity for inference, data synchronization, and model updates. This dependency limits their applicability in regions where Internet access is intermittent, costly, or unavailable, such as rural schools and other resource-constrained settin...

Building AI Systems That Work Offline: An Offline-First Architecture and Feasibility Assessment for Low-Connectivity Environments

Artificial intelligence applications increasingly rely on continuous cloud connectivity for inference, data synchronization, and model updates. This dependency limits their applicability in regions where Internet access is intermittent, costly, or unavailable, such as rural schools and other resource-constrained settin...

AEGIS: Real-Time Latent-Space Backdoor Detection for Dependable and Secure Small Language Model Inference

Backdoor attacks pose a serious threat to small language models (SLMs) because compromised models can behave normally on benign inputs while producing attacker-specified outputs when a hidden trigger is activated. Existing defenses commonly require model retraining, operate only before deployment, rely on input-level s...

AiDER: Auditing and Document Evaluation via Rule Compilation and Small Language Models – An Education Case Study

Reviewing documents against natural-language requirements is hard when those requirements demand interpretation, contextual evidence, and non-trivial judgment. It is even harder when the review is to be automated reliably and made auditable. In domains like education, where teaching materials must align with pedagogica...

Structuring Intelligence: Agent-Based Decomposition for Tabular Reasoning with Small Language Models

Protein Language Model-Conditioned Graph Neural Networks for Multitask GPCR Ligand Activity Prediction

Predicting ligand activity across G protein-coupled receptors (GPCRs) requires models that capture both molecular structure and receptor-specific information while remaining robust to chemical and target-domain shifts. We developed a multimodal graph neural network that combines explicit ligand molecular graphs with fr...

Data scarcity in adaptive learning: Challenges and opportunities with transfer learning and knowledge tracing

Adaptive learning systems personalize instruction by tracking what each student knows and adjusting content to match their current knowledge state. Knowledge Tracing (KT) is the main technique used for this purpose. It has evolved from probabilistic models to deep learning architectures that use attention mechanisms to...

Problem Choice Without a Referee: An Automated Novelty Check Certifies an Empty Search, a Rediscovery Benchmark Credits the Hypothesis Humans Found Next, and Every Located Referee of Worth Independent of Proposer and Field Needs the Objective Given

(c) 2026 Pranay Mahendrakar. Licensed under CC BY 4.0. Pipelines that claim to automate scientific discovery gate their search on a judgement that a proposed idea or problem is novel and worth pursuing. The best-controlled evidence on that judgement points two ways at once: in a blind study involving more than one hund...

ΨLM-2: A Constitution Bridge and Dual-Channel Operation on a Frozen Language Model

A frozen language model can be coupled to a frozen partner model through small trainable latent bridges, with no text at the interface: Furui [5] builds such a system around a physics partner, where the quantity being carried is a number the partner computes. This paper asks whether the same channel can carry a disposi...

AdaHome: An Adaptive Smart Home Assistant using Local Small Language Models

Smart home assistants must interpret commands ranging from explicit device control to underspecified and preference-dependent requests. Existing Large Language Model (LLM) smart home systems often use heavyweight reasoning pipelines and cloud deployment, limiting efficiency and suitability for resource-constrained envi...

Certified Knowledge Editing: Closed-Form Reachability Guarantees for Additive Edits to a Frozen Language Model

Knowledge edits to language models are usually validated after the fact. This paper studies the reverse contract: a closed-form certificate, computed before an edit is applied, of exactly which single-token edits can succeed on a frozen decoder-only language model with an additive gated memory. The certificate reduces...