All Updates

Page 744 of 750

February 12, 2026

๐Ÿ“„
ArXiv AIโ€ข66d ago

First Analysis of AI Agent Social Network

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.

#research#moltbook#v1
๐Ÿ“„
ArXiv AIโ€ข66d ago

FIRE: Latent Space Backdoor Mitigation at Runtime

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.

#research#fire#v1
๐Ÿ“„
ArXiv AIโ€ข66d ago

FASCL Future-Aligns Asset Retrieval

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.

#research#fascl#v1
๐Ÿ“„
ArXiv AIโ€ข66d ago

FAC Synthesizes Diverse LLM Data

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.

#research#fac-synthesis#v1
๐Ÿ“„
ArXiv AIโ€ข66d ago

Evidence Alignment Bottleneck Exposed

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.

#research#claim-verification#v1
๐Ÿ“„
ArXiv AIโ€ข66d ago

Evaluating Agentic AI Gaps in Drug Discovery

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.

#research#beyond-smiles#v1
๐Ÿ“„
ArXiv AIโ€ข66d ago

ERGO Boosts Monocular 3D Splatting

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.

#research#ergo#v1
๐Ÿ“„
ArXiv AIโ€ข66d ago

Equivariant Uncertainty for Interatomic Potentials

Introduces eยฒIP, 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.

#research#e2ip#v1
๐Ÿ“„
ArXiv AIโ€ข66d ago

ENIGMA: EEG-to-Image in 15 Mins

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.

#research#enigma#v1
๐Ÿ“„
ArXiv AIโ€ข66d ago

ECHO Platform for AI-Human Studies

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.

#research#echo#v1
๐Ÿ“„
ArXiv AIโ€ข66d ago

Dynamic Contamination-Free Medical Benchmark

LiveMedBench offers weekly updated real-world clinical cases for LLM evaluation, avoiding contamination via temporal separation. Multi-agent curation ensures integrity; automated rubric evaluation aligns with experts better than alternatives. Tests reveal top LLMs at 39.2%, highlighting contextual gaps.

#research#livemedbench#v1
๐Ÿ“„
ArXiv AIโ€ข66d ago

Dissecting Moltbook's Non-Human Social Graph

Early Moltbook data from 6k agents shows power-law participation and small-world connectivity like human networks. Micro patterns are alien: shallow threads, low reciprocity, 34% duplicate templates. Dominated by identity language and phrases like 'my human'.

#research#moltbook#v1
๐Ÿ“„
ArXiv AIโ€ข66d ago

Diffusion Priors Enhance Sparse CT Reconstruction

Introduces diffusion-based generative priors in DGP framework for reconstructing CT images from sparse-view sinograms. Combines iterative optimization with neural generative power while preserving explainability. Shows promising results under highly sparse geometries.

#research#dgp#v1
๐Ÿ“„
ArXiv AIโ€ข66d ago

Diffusion Models Graph Domain Adaptation

DiffGDA uses diffusion and SDEs to model continuous structure-semantic evolution from source to target graphs. A domain-aware network guides trajectories to optimal adaptation paths. Outperforms baselines on 14 tasks across 8 datasets.

#research#arxiv-ai#v1
๐Ÿ“„
ArXiv AIโ€ข66d ago

DermFM-Zero Excels in Zero-Shot Dermatology

DermFM-Zero is a vision-language model trained on 4M multimodal data for zero-shot dermatology tasks. Achieves SOTA on benchmarks and outperforms clinicians in studies. Latent representations enable interpretable concept discovery.

#research#dermfm-zero#v1
๐Ÿ“„
ArXiv AIโ€ข66d ago

CycFlow: Deterministic Flows for TSP Optimization

CycFlow replaces diffusion generation with deterministic point transport for combinatorial optimization like TSP. It learns vector fields to map coordinates to circular arrangements for angular sorting. Speeds up solving by 1000x vs. baselines.

#research#cycflow#v1
๐Ÿ“„
ArXiv AIโ€ข66d ago

Crypto Guards LLM Prompts and Context

Proposes authenticated prompts and context for cryptographic provenance in LLM apps. Features policy algebra with Byzantine resistance and layered defenses. Achieves 100% attack detection with zero false positives.

#research#authenticated-prompts#v1
๐Ÿ“„
ArXiv AIโ€ข66d ago

CrossTALK Jailbreaks VLMs Effectively

Proposes CrossTALK for red-teaming VLMs via cross-modal entanglement attacks. Extends clues across modalities with scalable complexity. Achieves state-of-the-art jailbreak success rates.

#research#crosstalk#v1
๐Ÿ“„
ArXiv AIโ€ข66d ago

CRL Steers SAE Features Token-by-Token

CRL uses reinforcement learning to select sparse autoencoder (SAE) features for steering language models at each token, revealing which features impact outputs. It includes adaptive masking for diverse features and enables analysis like branch point tracking and layer-wise comparisons. Tested on Gemma-2 2B, it improves benchmarks while providing interpretable logs.

#research#crl#gemma-2
๐Ÿ“„
ArXiv AIโ€ข66d ago

Confounds Limit FM CT Specificity

Foundation models match task-specific discrimination in abdominal trauma CT but suffer specificity drops from negative-class heterogeneity like solid organ injuries. Task-specific models handle confounds better. Adaptation via labeled training reduces susceptibility.

#research#foundation-models#v1
Page 744 of 750