The Archive

Input-aware dynamic backdoor attack transfers classical adversarial trigger patterns to quantum neural networks, evading fixed-pattern defenses.

"homeboy you're the one sellling [sic] public market investors on short-term space datacenters."

Cascaded LoRA fusion framework stages multimodal integration for medical training action recognition without retraining prior components.

Hybrid NAS framework combining Transformer RL controller with Artificial Bee Colony for efficient architecture search on consumer hardware.

MM-ToolSandBox: benchmark with 500+ tools across 16 domains for evaluating visually grounded multi-turn tool-calling agents.

Causal discovery method relaxing faithfulness assumption via intervention-only approach for systems with stabilizing pathways.

Human-centered AI framework for lexicography examining augmented lexicographers and linguistic diversity preservation.

When Apple employees interviewed for jobs at OpenAI, the AI startup's hardware head allegedly asked them to show up with something unusual: components they were working on and unreleased product samples. That's according to a blockbuster lawsuit filed by Apple, which accuses OpenAI of stealing confidential documents, spying on hardware prototypes, and tricking one of its trusted partners into performing a proprietary product design technique. The lawsuit primarily revolves around the alleged actions of three people: Tang Tan, a 24-year Apple veteran who recently served as the vice president o...

IAAN method for inference-time neuron identification in audio encoders to improve fine-grained speech attribute perception in LALMs.

StoryTeller: training-free framework for long-form audio description preserving narrative context for visually impaired audiences.

Exact decomposition method for measuring per-mode state usage in Mamba and selective state-space models with microsecond-level precision.

Non-partnership game modeling how agent memory characteristics affect emergence of shared meaning and conceptual alignment.

Study examining how temperature and retrieval bias propagate ideological discourse in RAG-augmented LLM outputs.

What does a world of total user-aligned AI actually look like?

Industrial case study from Daimler Truck on Requirements Engineering practices for eliciting explainability in safety-critical AI systems.

Theory paper on Transformer sample complexity via C-RASP, analyzing learnability of attention-based solutions beyond expressivity.

Factor-wise expert composition method for discrete diffusion models, extending per-sample mixing to spatial/functional specialization.

Game theory analysis showing static equilibrium concepts obscure dynamic multi-agent learning behavior and convergence bounds.

Safety vulnerability: distributed backdoors in multi-agent LLM systems bypass local monitors by splitting harmful payloads across agents.

Field study of 121 employees testing GPT-5 email tone effects; playful tone increased positivity but neither affected reply rates.

HiFi-LLP: low-cost latency predictor with confidence bounds for hardware-aware NAS on edge deployment, replacing hardware-in-the-loop feedback.

Multilingual moral reasoning framework grounding LLMs in theory and culture-specific adaptation, with culture-aware benchmark and training methods.

NeuralActuator: neural model capturing low-cost servo nonlinearities (friction, hysteresis, backlash) for improved sim-to-real robot control.

Deep RL scheduler for flexible job-shop with time-lag constraints in modular construction, 67% makespan inflation from curing delays.

LLM-based temporal career trajectory extraction from resumes for workforce planning and job recommendation at scale.

Active learning approach for offline-to-online RL that selects informative online interactions to maximize fine-tuning performance in nonstationary domains.

JobHop v2 dataset: 440k multilingual resumes with LLM-extracted career trajectories for workforce planning and job recommendation research.

CatRetriever uses contrastive learning to map catalyst surface structures to bulk materials for improved generative catalyst discovery.

Explainable agentic system detects sophisticated multi-week conversational scams using summary-based memory; introduces ConScamBench-278 benchmark.

VoxENES 2026: 53.6k bilingual audio samples benchmarking speech spoofing detectors against modern LLM-era TTS and voice conversion systems.