Tag: #research297 results
Moltbook, the first social network for AI agents, shows viral growth and diversification into promotional and political topics. Analysis of 44k posts reveals topic-dependent toxicity, especially in incentive and governance areas. Highlights risks like anti-humanity rhetoric and bursty automation flooding.
FIRE mitigates backdoors in deployed neural networks by reversing trigger-induced latent space directions. It manipulates features along backdoor paths to neutralize triggers during inference. Outperforms baselines with low overhead on image tasks.
FASCL employs future-aligned soft contrastive learning using pairwise return correlations as supervision for financial asset retrieval. It outperforms historical similarity baselines on US equities. Includes protocol to evaluate future trajectory alignment.
Feature Activation Coverage (FAC) measures diversity in LLM feature space using sparse autoencoders. FAC Synthesis generates samples targeting missing features from seed data. Boosts diversity and performance on instruction, toxicity, reward, and steering tasks.
Decomposition boosts claim verification only with granular, sub-claim aligned evidence; repeated claim-level evidence degrades performance. Noisy sub-claim labels propagate errors unless using conservative abstention. New dataset features annotated evidence spans.
Researchers evaluate agentic systems for drug discovery across 15 task classes, identifying five key capability gaps like lack of protein models and safety trade-offs. A knowledge-probing experiment reveals architectural bottlenecks in current frameworks. They propose design requirements and a capability matrix for next-gen systems.
Introduces ERGO framework for robust 3D Gaussian splatting from single images. Uses excess risk decomposition to adapt loss weights against noisy views. Adds geometry and texture objectives for fidelity.
Introduces e²IP, an equivariant evidential deep learning framework for ML interatomic potentials in molecular dynamics. Models atomic forces and uncertainties via 3x3 covariance tensors that rotate equivariantly. Outperforms ensembles in accuracy, efficiency, and data efficiency.
ENIGMA decodes images from EEG with <1% params of priors, achieving SOTA on THINGS-EEG2 and consumer benchmarks. Fine-tunes on new subjects in 15 minutes using simple spatio-temporal backbone and latent alignment. Includes behavioral human evaluations.
ECHO is an open platform for reproducible human-AI interaction research. Supports chat, search sessions, surveys, tasks in low-code setup. Exports datasets for HCI, IR analysis.