The Archive

BayesAME automatically determines coreset size for efficient LLM benchmark evaluation using sequential Bayesian inference.

Stereotypes-to-Decisions framework measures regional bias in six LLMs across China's 34 provinces, linking abstract stereotypes to concrete allocation decisions.

Certificate-gated protocol determines which physical parameters (mass, drag, stiffness) latent world models actually internalize from raw visual observations.

OpenAI reports 3x improvement on ARC-AGI-3 benchmark via two API settings enabling reasoning retention and compaction in GPT-5.6.

Overlap gap property extended to finite-temperature neural network optimization, characterizing algorithmic accessibility of noisy solutions.

AgentSnare uses adaptive deceptive observations to mislead LLM-based penetration testing agents, defeating static artifact recognition.

24 frozen vision foundation models (ViT, CLIP, etc.) evaluated for face presentation attack detection via linear probing under domain shift.

Algebraic framework deriving transformer expressivity from finite-precision attention dynamics and memory constraints.

The startup analyzes calls, messages and CRM data to identify effective sales techniques and turn them into playbooks for AI agents.

SymmGrid framework accelerates on-robot reinforcement learning via parallelized symmetries and dual visual perception.

LLM-based validation of atom-centered structural descriptors reveals descriptor degeneracies in materials science.

OptimismBench detects directional bias in LLM probability judgments via inverted-pair evaluation method.

TREK benchmark evaluates LLM agents on complex, executable travel itinerary planning with verifiable constraints.

Pair-level judgment outperforms dialogue-level generation for emotion-cause extraction in conversation datasets.

Feature stability analysis framework shows feature bagging ensemble reduces generalization error.

BAND sparse Bayesian network achieves polynomial convergence rates for high-dimensional distribution estimation.

CreditCardQA benchmark evaluates LLM numerical reasoning on real financial documents with CoT/PoT comparison.

Progressive Multimodal Alignment mitigates projector drift in continual instruction tuning of vision-language models.

Belief-Guided architecture reduces Monte Carlo Tree Search dependency in Computer Go, improving inference on consumer hardware without deep search hallucinations.

Surrogate-guided dual-objective search method for neural ensemble search addresses computational intractability of joint architecture and composition optimization.

Three-class detection framework distinguishes humans, bots, and AI agents in browser automation traffic; binary classifiers misclassify 39.1% of agents as human.

FedDAB defends federated learning against backdoor attacks via model-contrastive regularization and alignment checking, addressing statistical heterogeneity.

Paired-prompt methodology tests whether language models correctly match diagnostic evidence to causal claims across different populations and estimands.

Latent-IM recovers state estimation and action control for conversational moves in speech LLMs by decomposing move selection and realization in hidden representations.

Temporally centered SIGReg improves multi-task latent world-model learning by maintaining task-dependent cluster separation during marginal Gaussianization.

Two-call self-refinement outperforms five-agent pipeline on Qwen2.5-7B; multi-agent systems suffer error accumulation, dropping GSM8K accuracy to 45% with JSON format.

BioVLN simulation platform for visual-language navigation in biomedical labs with instrument-specific approach constraints and safe clearance requirements.

DuPLeR dual-path LLM reasoning framework combines multimodal and LLM priors for few-shot knowledge graph completion while filtering hallucinated evidence.

Formalizes detection of outcome performativity—when predictions causally influence predicted outcomes—via A/B intervention testing in palliative care, credit, recommender systems.

Pegasus framework translates human manipulation videos into robot-learnable data via task graphs and affordance constraints, addressing embodiment gap for embodied AI.