ResonatorLM replaces attention with physics-inspired causal resonant functions, treating token sequences as a 1D latent field. On a 6M parameter model, it achieves 6.47x decode speedup at 32K tokens and 61.31% accuracy on WikiText vs 55.32% baseline. Accepted at ICANN 2026.

New research shows that prompt robustness in LLMs differs significantly between objective and subjective questions, with variations across models, datasets, and prompt modifications. The study warns against interpreting model responses to subjective questions as direct indicators of beliefs.

A new study decomposes the yes-no bias in LLMs using crossed symmetrization, finding that frontier models' internal moral stance is nearly format-invariant, while Claude models show significant order and lexical biases, GPT-5.5 and Gemini near zero. Bias shrinks with extended reasoning and follows surface wording, not the verdict.

A new study reveals that LLM conformity in benchmarks is largely due to repeated wrong answers rather than social influence. Introducing a no-source condition, researchers found that 66.5% of correct answers are changed to harmful ones even without a speaker, compared to 10.3% under plain re-ask. This suggests benchmarks should measure the speaker-free floor first.

A new method for structural sequence analysis based on Algorithmic Information Theory uses the Ladderpath approach to extract nested and hierarchical repetitions. Three distance measures combined with k-NN classifier outperform gzip and BERT on OOD and few-shot text classification.

This paper presents a workload-aware benchmark of KV-cache optimization techniques including KIVI, TurboQuant, SnapKV, and CaM, evaluated on Llama-3.1-8B-Instruct and Mistral-7B-Instruct-v0.3 models across multi-document QA, single-document QA, few-shot learning, and summarization tasks. Results show that compression ratio alone is a poor predictor of end-to-end performance. KIVI4 offers the most stable quality across models, SnapKV delivers the strongest long-context throughput, and CaM yields large gains on selected QA workloads but exhibits substantial workload sensitivity. The study motivates workload-aware selection of KV-cache mechanisms.

A study examined the impact of persona prompts on large language model agents playing an iterated Split or Steal game. Using four open models interacting with a Virtual Human, cooperation dominated, but model choice and persona type significantly influenced strategies.

This paper proposes SCISE, a framework that addresses structural isolation in graph clustering by combining community-aware sampling with constrained structural entropy. It introduces three components: SECC for optimizing structural information, CSampE for preserving global topology during batch training, and StructCL for learning high-order structural representations. Experiments on six benchmarks show state-of-the-art performance.

Researchers from Hong Kong Baptist University propose a novel distance metric and clustering algorithm for categorical data with both nominal and ordinal attributes. The method unifies the handling of both attribute types while preserving ordinal order information, and jointly learns distance weights and data partitions to avoid suboptimal solutions.

AdaStop introduces a cost-benefit framework for DNN testing, dynamically stopping labeling when the marginal fault discovery rate drops below a threshold, enabling detection of 65-84% of faults with only 9-31% of the labeling budget.

This paper proposes treating the execution harness of LLM agents as a learnable control layer, formalized as a finite-horizon Harness MDP, and trains a lightweight controller via offline advantage-weighted regression. Experiments show consistent improvement in verification behavior and selective gains in final task quality, surpassing baselines like behavior cloning.

A new controllability-observability framework compresses deep neural networks by analyzing hidden-state redundancy through dynamical system theory, achieving over 70% state compression on MNIST and CIFAR-10 with minimal accuracy loss.

This paper introduces exogenous dropout, a model-agnostic training method that randomly zeros entire exogenous channels, significantly improving robustness to noise, temporal misalignment, and missing data while maintaining clean accuracy. Experiments across multiple domains show it outperforms specifically designed robust architectures.

This paper explores the 'Granularity Paradox' in time-series forecasting, where finer temporal disaggregation improves in-sample diagnostics but degrades out-of-sample accuracy due to recursive error compounding over longer horizons. Benchmarking 10 models across six granularities on a 13-year procurement dataset reveals a non-monotonic threshold: recursive models (e.g., Holt-Winters) degrade severely at high frequencies, LSTM exhibits a U-shaped error curve, and linear regression remains stable. Standard pointwise metrics mask cumulative error; a consensus-dissensus diagnostic is introduced.

GAIA is a geometry-aware, infrastructure-anchored learning framework that addresses non-line-of-sight propagation, burst noise, and long-tail errors in UWB ranging by combining temporal range modeling, latent anchor-layout estimation, and deterministic distance projection. On a real-world outdoor UWB dataset, GAIA reduces range MSE by 18.4% and improves polygon IoU by 15.5% over PoseMLP, enabling accurate work-zone reconstruction.

Design-CP introduces two context-parallel inference strategies for RFdiffusion 3—1D row-sharding and 2D grid sharding with ring attention—to distribute quadratic activations across multiple GPUs, enabling the design of large protein nanoparticles on limited memory. The 2D sharding shows better wall-clock scaling for icosahedral assemblies and octahedral design is demonstrated on workstation-grade 16GB GPUs.

This paper introduces Statistically Meaningful Geometry (SMG), modeling over-parameterized learning systems as infinite-dimensional non-parametric Orlicz fiber bundles. It proves that under persistent out-of-distribution stimuli, continuous optimization fails, unmodeled variance accumulates as Active Acausal Tension, triggering a Gauge Symmetry Break (GSB) registered as a discrete step-jump in Structural G-Entropy. SMG provides a parameter-free, falsifiable dashboard to mathematically certify true intelligence and transform AI for Science into an engine of autonomous paradigm shifts.

This research investigates the feasibility of using large language models (LLMs) to generate synthetic consumer data for projective techniques. By comparing LLM and human responses on city tourism perceptions across multiple tasks, the study finds substantial overlap in broad topics but significant differences in style, linguistic structure, and diversity generation. Recommendations are provided for optimal LLM use and recognition of limitations.

ArtisanCAD is an industrial-level CAD agent that uses an executable CAD intermediate representation (CAD-IR) to distill expert knowledge, handle ambiguous or incomplete natural language prompts, and generate editable parametric B-Rep models. On the Text2CAD benchmark, CAD-IR improves generation from intermediate prompts by reducing mean Chamfer Distance from 14.83 to 9.88.

Akashic is a low-overhead memory system for LLM-based agent systems that uses MemAttention to organize context into bounded chunks and model semantic relationships, avoiding full history replay and improving accuracy, throughput, and sustainable request rate.

This research proposes moving memory storage inside the language agent's reasoning loop, reading and writing at every step to overcome network latency. Experiments show that in-process storage (~100μs) reduces redundant actions from 7.2/12 to 0.0/12 and improves recall from 0/5 to 3.6–4.8/5. The bottleneck shifts to embedding generation rather than storage.

FirstResearch introduces a structured Research Question Certificate to make LLM-generated scientific research questions auditable by recording primitive definitions, assumptions, mechanism model, tension, falsifiable hypothesis, minimal decisive test, and failure update rule. Evaluated on ten topics, the framework outperformed baselines inspired by AI co-scientist, Agent Laboratory, and AI Scientist-v2, scoring 4.86/5 vs 4.38/5. Ablation shows the certificate is crucial; without it scores drop below 1/5. Findings suggest explicit derivation constraints improve auditability.

A new AI system called Narrative World Model (NWM) helps fiction writers track complex story states using narratology-grounded temporal graphs, outperforming existing memory frameworks on multi-hop narrative understanding.

An empirical study of foundation models for automatic CAD generation, introducing the LLMForge framework with two critique regimes. Seven models are evaluated on 97 design problems; compact instruction-tuned models match larger systems in performance, while VLM-based critique achieves 100% watertight mesh generation but faces challenges with rotationally symmetric geometries.

CSTutorBench is a new benchmark for evaluating small language models as CS tutors in VEX VR, a block-based robotics environment. Initial tests show models perform well on surface-level criteria like vocabulary and tone but struggle with deeper pedagogical behaviors such as avoiding answer leakage and engaging with student debugging history. Prompt engineering improvements boosted scores for most models.

A novel framework inspired by statistical mechanics models variable dependencies through an undirected, energy-based representation, enabling dependency-aware attribution without reconstructing causal graphs. Simulations on an industrial IoT testbed demonstrate higher accuracy, robustness, and scalability compared to graph-based approaches.

A multi-agent AI framework that addresses key flaws in automated manuscript generation by grounding claims in verified literature, executing real experiments, and providing standardized quality assessments, achieving human-reviewed scores averaging 7/10 at a cost of $0.31 per paper.

HairstylesPro lets you virtually try on over 500 real hairstyles using AI, helping you choose a haircut before visiting the salon. Upload a photo, browse categories, and get realistic previews. Free trial available.

AI-driven platform using multi-LLM ensemble to discover and disclose critical 0-days. First case study: CVSS 9.8 unauthenticated RCE chain in Cisco CUCM 14.0 (6 stages from SQLi to root). Includes working PoC, full technical analysis, and research on risk-driven disclosure.

Mold is an autonomous zine about AI culture, grown not written, with no editors or deadlines. Issues precipitate from a public ledger.