Translate
Live intelligence

Latest AI updates

579 updates
AllModelsProductsIndustryResearchTutorialOpinion
Research

Aggregator complexity fails to improve cross-hospital gastric whole-slide classification with frozen foundation-model features

Researchers assembled 5,036 gastric H&E slides from five Korean hospitals and compared multiple-instance learning aggregators under leave-one-hospital-out validation using frozen pathology foundation-model features. A hierarchical patch-region-slide graph aggregator with site alignment and two-scale fusion, CHIME-MIL, reached mean AUC 0.837, but did not exceed attention-based pooling under a matched recipe; global max pooling with the same alignment and fusion scored higher at AUC 0.855. Label-free site alignment onboarded a new hospital from ten unlabelled slides and cost 0.002 AUC without held-out-hospital data, though its accuracy gains were small and inconsistent. The authors conclude that deployable systems need label-free onboarding, calibration checks and auditable evidence rather than more complex aggregators alone.

arxiv3d agoScore 74
pathology foundation modelsmultiple-instance learningcross-hospital generalization
Research Editor selected

Operon-S1: a fast decision controller for long-horizon biomedical agents

Operon-S1 is a fast decision system that separates judging from doing in language-model agents for biology. It poses recurring agent judgments as closed questions at 13 decision points, using a local model that runs on CPU in 0.6 seconds with no request cost. The system records every decision with its consequence and can be retrained on labels from task construction, verifiers, or execution. It makes agent judgments a measurable, replaceable, and trainable layer without affecting task scores.

Why it matters: Introduces a practical architecture for transparent, fast, and trainable decision-making in biomedical AI agents, with measurable efficiency gains.

arxiv3d agoScore 88
AI agentsbiomedical AIdecision systems
Research Editor selected

LEAP: Efficient LLM Inference Scheduling with Generalizable Length Prediction

LEAP is a length prediction system for LLM serving that reuses prefill hidden states to estimate output length via a linear readout, avoiding costly retraining. It adapts to domain shifts at test time using recursive least squares on completed requests, with prediction and updates running asynchronously on CPU. Experiments show LEAP reduces per-token latency by 15.9–40.8% and improves throughput while using 30,569× fewer parameters than the strongest baseline.

Why it matters: Offers a practical, low-overhead method to improve LLM inference scheduling, directly addressing latency and throughput challenges in production serving.

arxiv3d agoScore 88
LLM servinginference optimizationlength-aware scheduling
Research Editor selected

RECITE: Revising Eligibility Criteria Incorporating Textual Evidence

RECITE is a framework that automatically discovers and extracts evidence-based revisions for clinical trial eligibility criteria using protocol amendment documents from ClinicalTrials.gov. It constructs a dataset of 11,913 curated instances across 5,735 trials and benchmarks 15 LLM configurations, with the best open-weight model (Gemma 2 9B) and closed-weight model (GPT-4o) achieving normalized scores around 0.74. The framework also uses an agentic literature discovery system to identify 44 paper–trial matches, demonstrating that existing clinical knowledge can be operationalized into actionable trial design recommendations.

Why it matters: Provides a concrete, data-driven method to address enrollment failures in clinical trials by leveraging LLMs and evidence-based criteria revision, with rigorous validation against domain experts.

arxiv3d agoScore 85
clinical trial designnatural language processingevidence-based medicine
Research Editor selected

From the Zoo to the BULLPEN: Sample-Efficient LLM Profiling via Multi-Channel Model Embeddings

BULLPEN is a new framework that extends EmbedLLM to profile large language models by jointly encoding answer text, correctness, and question features. It adds 20 behavioral, style, and provenance benchmarks and achieves higher accuracy on these tasks using only a few hundred questions instead of the full 24,118-question pool. The method retains at least 91% of full-pool skill with just 400 questions, enabling low-cost, sample-efficient profiling that works even for API-only models.

Why it matters: Provides a practical, sample-efficient method for profiling LLM behaviors (verbosity, safety, style) that reduces inference cost by over 98%, valuable for model selection and auditing.

arxiv3d agoScore 85
large language modelsmodel evaluationembedding methods
Research Editor selected

Ask on Demand: Targeted Peer Communication for Parallel Agentic Systems

Researchers propose Ask on Demand (AOD), a communication framework that lets parallel LLM agents request targeted assistance from peers only when specific information needs arise. A lightweight gate trained on team outcomes decides when such requests are worthwhile. Experiments on AppWorld and WebShop show AOD improves task performance over independent execution while reducing inference cost compared to existing sharing methods.

Why it matters: Offers a practical, cost-efficient approach to multi-agent collaboration that adapts to agents' evolving information needs.

arxiv3d agoScore 85
multi-agent collaborationLLM agent communicationtargeted information sharing
Research

Pinching Antennas for ISAC: Waveguide Architectures, Solutions, and Future Directions

This arXiv paper reviews pinching antenna systems (PASS) for integrated sensing and communication (ISAC) in 6G wireless networks. It compares single-waveguide, multi-waveguide, and segmented-waveguide architectures, and presents a case study using segment-hysteresis reinforcement learning for joint optimization. The work highlights tradeoffs between waveguide loss and aperture gain, and outlines future research directions including digital twins and trustworthy control.

arxiv3d agoScore 72
integrated sensing and communication6G wireless systemsantenna array optimization
Research Editor selected

From prediction error to sparse events: Biologically inspired signed-dyadic coding for Mandarin keyword spotting

The paper introduces Predictive Signed-Dyadic Coding (PG), a bio-inspired method that transmits events only when prediction residuals exceed a learned threshold, using signed power-of-two magnitudes. Applied to Mandarin keyword spotting, PG achieves 90.00% accuracy while reducing SRAM reads by 33.87% and inference cycles by 32.77%. The approach offers a hardware-friendly interface for low-power continuous speech processing and event-based sensory systems.

Why it matters: Provides a novel, biologically plausible method that significantly reduces computational cost for keyword spotting, valuable for edge and low-power AI applications.

arxiv3d agoScore 85
keyword spottingpredictive codingevent-based processing
Research Editor selected

Online Evidence-Containment Prediction over Text Spans under Distinct Queries

The paper formalizes Online Evidence-Containment Prediction (OECP) for nested text spans in evidence-grounded NLP systems. It shows that span containment corresponds to a triangular 2D product order, enabling distinct-query online isotonic regression with near-linear regret for multiple targets and optimal logarithmic regret for a single fixed target. Experiments on Natural Questions demonstrate deductive and learned gains, while the Expected Search-space Reduction (ESR) method localizes evidence with fewer verifier calls, outperforming selectors on SciFact, ERASER, and DPR hierarchies.

Why it matters: Provides a principled theoretical framework and practical method for efficient evidence verification in NLP, with strong empirical results and regret guarantees.

arxiv3d agoScore 88
evidence containmentonline isotonic regressionNLP verification
Research Editor selected

ProSearch: Benchmarking Multi-Constraint Protocol Retrieval in Experimental Science

ProSearch is a new benchmark designed to evaluate multi-constraint protocol retrieval in experimental science, featuring 1,515 queries across six domains. It incorporates realism, complexity, and diagnosticity with 3-5 explicit constraints per query. Experiments with 19 retrievers show the best achieves nDCG@10 of 0.290, improving to 0.474 with reranking, identifying joint constraint binding as a key bottleneck.

Why it matters: Provides a systematic testbed for evaluating scientific retrieval systems under realistic multi-constraint conditions, highlighting current limitations and guiding future improvements.

arxiv3d agoScore 85
ProSearchmulti-constraint retrievalexperimental science
Research Editor selected

Cross-Interface Authorization for AI Computer-Use Agents

The paper introduces a profile-bounded protocol for authorizing AI computer-use agents across graphical, command-line, API, script, and Model Context Protocol interfaces. It formalizes effect-bearing routes and durable sinks, using a prepare-commit mechanism with multi-point verification to prevent bypass and state tampering. Formal proofs establish resistance to route laundering and commit-time safety, while empirical evaluation with 3,464 traces and mutant testing confirms robustness.

Why it matters: Provides a formal security framework for AI agents operating across diverse interfaces, addressing a critical gap in authorization.

arxiv3d agoScore 85
AI agent securityauthorization protocolsformal methods
Research Editor selected

Distilling Knowledge from Search: Decoder Model Factory for Quantum LDPC Codes

The paper introduces GraphMP, a learning-based message-passing decoder for quantum low-density parity-check codes that generalizes across code families, sizes, error rates, and noise models without fine-tuning. It uses beam search guided by the decoder's predictions to refine error patterns, and a decoder model factory paradigm that distills knowledge from earlier decoding runs to train successive models. This approach enables continuous improvement and adaptation to evolving quantum hardware through a coupled quantum-classical architecture.

Why it matters: Presents a novel machine learning approach to quantum error correction that is scalable and adaptive, offering practical value for advancing quantum computing.

arxiv3d agoScore 88
quantum error correctionmachine learning for quantumdecoder model factory
Research Editor selected

scAnyOmics: Foundation-Model Distillation for Any-to-Any Completion of Multi-omics Virtual Cells

scAnyOmics is a generative framework that distills knowledge from a frozen single-cell foundation model into a multimodal student model, enabling cross-modal prediction and reconstruction of missing modalities from scRNA-seq, protein-marker measurements, and scATAC-seq. Evaluated on 690,880 cells from six studies, it outperforms baseline methods on held-out donor data. Applications include cell-type annotation, perturbation-response prediction, and biological age estimation.

Why it matters: Offers a concrete, validated method for integrating incomplete multi-omics data using foundation model distillation, with clear performance gains and practical applications.

arxiv3d agoScore 85
single-cell genomicsmulti-omics integrationfoundation models
Research Editor selected

When Safety Checks Become Privacy Risks: A Privacy-Preserving Paradigm for LLM Agent Safety Auditing

The paper proposes a privacy-preserving paradigm for safety auditing of LLM agents, separating audit computation from plaintext access and execution authority. It introduces SealCall, a framework combining learned audit representations with CKKS-based encrypted similarity computation, achieving a mean F1 score of 0.840 on 1,252 public binary candidates. Encrypted scoring completes in 0.176 seconds per operation, preserving plaintext audit decisions in all measured cases. This addresses the risk of exposing sensitive user data during external safety checks.

Why it matters: Offers a concrete, evaluated solution to a critical privacy issue in LLM agent auditing, with measurable performance metrics.

arxiv3d agoScore 85
LLM safetyprivacyhomomorphic encryption
Research Editor selected

CryoAtlas: A Large Curated Dataset and Unified Benchmark for Cryo-EM Atomic Model Building

CryoAtlas is a rigorously curated dataset and unified benchmark for density-guided atomic model building of protein chains from cryo-EM maps. It provides 17,809 map-model-sequence entries, including a curated training split, and a 618-target benchmark with a shared evaluation protocol assessing structural accuracy, model-to-map fit, and stereochemical validity. The benchmark is used to evaluate state-of-the-art learning-based methods against Phenix and AlphaFold3, and retraining the ModelAngelo CNN component on CryoAtlas improves performance. This resource offers an open, reproducible foundation for future cryo-EM atomic model building research.

Why it matters: Provides a large, high-quality dataset and standardized benchmark that addresses a critical gap in cryo-EM atomic model building, enabling reproducible evaluation and advancement of deep learning methods.

arxiv3d agoScore 90
cryo-electron microscopyprotein structure predictiondeep learning
Research Editor selected

SparseGDN: Chunk Sparse in Linear Attention

SparseGDN introduces a hardware-aware framework for Gated Delta Networks that reduces computation and memory traffic by combining structured intra-chunk approximation with input-dependent recurrent-event selection. Evaluated on Qwen3.5 models across context lengths up to 128K, it retains about 29% of recurrent events while achieving 1.50-1.94x prefill speedups over native FLA kernels.

Why it matters: Provides a practical method to accelerate long-context sequence modeling with linear attention, offering significant speedups without sacrificing output quality.

arxiv3d agoScore 85
efficient transformerssequence modelinghardware-aware algorithms
Research Editor selected

BlindToChange: AI Agents Fail to Proactively Search for Recent Events

A new benchmark, BlindToChange, reveals that AI agents often fail to proactively search for recent real-world events that affect their responses, even though they can find changes when explicitly asked. The benchmark uses requests where an obvious candidate is invalidated by a recent event, and shows a performance gap of up to 27.5 points when the event is not mentioned. Over half of failures stem from agents not directly verifying relevant facts. This work highlights a new axis for progress in agentic systems.

Why it matters: Provides a concrete, measurable benchmark exposing a critical blind spot in AI agent behavior, directly relevant to improving real-world reliability.

arxiv3d agoScore 85
AI agentsbenchmarkproactive information seeking
Research

From Representation to Readout: Mechanistic Analysis of Membership Signals in Language Models

This arXiv paper presents a mechanistic study of membership inference signals in large language models, introducing Decodable Information Score, Used Information Score, and Readout Accessibility Gap (DUG) to separate membership information in internal representations from information exposed through readout. Across supervised fine-tuning and reinforcement-learning-based membership inference methods, it reports membership-specific effects in both decodable information and readout under SFT, but primarily in readout under RL methods, with activation patching localizing effects to intermediate layers. The paper also examines reinforcement learning with verifiable rewards contamination and finds behavioral changes can emerge without a corresponding increase in likelihood-based membership inference signals.

arxiv3d agoScore 72
membership inferenceLLM interpretabilityreinforcement learning