small language model

Vision-Language Models for Egocentric Video: From Hand-Object Interaction to Embodied AI

This survey presents a critical review of VLMs for egocentric video understanding, tracing the progression from conventional recognition architectures to multimodal foundation models and embodied systems, and examines how first-person perception and multimodal foundation models support wearable assistance, robot skill...

Mechanistic Tomography: Designed Measurement for Control-Oriented Interpretability

Mechanistic interpretability seeks quantities that models do not expose directly: represented states, component effects, interactions, and responses to interventions. Patching, gradients, Hessian-vector products, and subset interventions provide different measurements under different access assumptions and may target d...

Where Grounding Accuracy Lives on the IoU Curve: Label-Free Inference-Time Boundary Refinement

The results show that referent selection and boundary precision are partially separable, with different components moving opposing regions of the IoU curve -- behavior a single threshold cannot reveal.

Daedalus-150M: A Convolution-Attention Hybrid Designed for CPU Inference

A conventional all-attention model of the same size on the same data and a conventional all-attention hybrid that beats GPT-2 124M, Pythia-160M, OPT-125M and GPT-neo-125M, and exceeds MobileLLM-125M's published score despite that model seeing a trillion tokens.

Automated Summarization of Financial News Using Large Language Models and Retrieval-Augmented Generation: An Early Empirical Study (Fall 2023)

This project built a pipeline that pulls news articles from the News API, company background from Wikipedia, and stock price data from Yahoo Finance for ten major companies and developed a simple but effective template that converts stock data into natural language narratives.

G3Ego: Gaze-Guided Graphs for Egocentric Action Understanding

G3Ego, a graph-based framework for egocentric action understanding that uses gaze as a structural cue to identify action-relevant entities in the scene, achieves competitive performance compared with video-based approaches and consistently improves Macro-F1 under class-imbalanced evaluation, while avoiding reliance on...

SafeBranch: Branch-Pair Safety Alignment for Embodied Agents

SafeBranch is proposed, a framework that aligns an embodied actor on safety through branch pairs constructed from the actor's own unsafe rollouts via environment rollback, achieving roughly ten times more safe successes than the untrained baseline on the unseen-object variant.

An Agentic Approach for Active Data Collection, Travel Behavior Modeling, and Weather-Sensitive Demand Prediction

Overall, the study shows how conversational surveys, structured data processing, conventional behavioral modeling, machine learning, and multimodal LLM prediction can be coordinated within an auditable multi-agent workflow.

Phantom Gains: Auditing Self-Improvement Against a Measured Null

Auditing three rounds of rank-$32$ LoRA self-training on Qwen3-8B against a frozen control pushed through the identical pipeline, this work identifies seven measurement failures, each of which inverts a reported finding when its control is absent.

SYNGAP1-related disorder: pathophysiology, epilepsy, cognitive and behavioral phenotypes, and precision therapeutic approaches.

A rapidly advancing precision-therapy pipeline-including antisense oligonucleotides to upregulate the intact allele, AAV-based gene replacement, CRISPR-mediated transcriptional activation, epigenetic modulators, and rational pathway-targeted small molecules-offers realistic prospects for disease modification.

Leveraging small language models for model predictive control of dynamic systems

Constitutional Midtraining: Content Presence Drives Alignment Gains

Post-training alignment is often shallow, eroding under fine-tuning. It remains untested as to whether constitutional midtraining interventions can produce durable alignment when cleanly isolated from post-training. We build a 394M-token constitutional corpus from Anthropic's Constitution and apply constitutional midtr...