Translate
Live intelligence

Latest AI updates

579 updates
AllModelsProductsIndustryResearchTutorialOpinion
Research Editor selected

General-purpose foundation models outperform specialized chemical FMs on property prediction with scarce data

A new arXiv study compares specialized chemical foundation models (ChemBERTa, MoLFormer) with general-purpose models (GPT-6 Astra, Claude Opus 5.5) on chemical property prediction tasks. With only 60 experimental datapoints, GPT-6 Astra outperforms the chemical FMs on five regression tasks. Chemical FMs only match Astra's performance when given 10x more data, suggesting general-purpose models are better for data-scarce chemistry research.

Why it matters: This finding challenges the common assumption that domain-specific models are superior in specialized fields, offering practical guidance for researchers in chemistry and AI.

arxiv3d agoScore 82
foundation modelschemistryproperty prediction
Research

ArchOR: Structure-Aware Skill Retrieval Improves LLM Optimization Modeling

ArchOR is a new archetype-centric skill agent for LLM-based optimization modeling, building on OptSkills with two retrieval modules: Centroid-Aware Representation Learning (CARL) and Signature-Guided Retrieval (S3R). It achieves 65.00% Micro-Avg. Pass@1 across five benchmarks, improving over OptSkills by 1.64 pp Micro-Avg. and 2.68 pp Macro-Avg. The method uses structural signatures and a baseline-preserving arbitration rule to enhance robustness under narrative rewrites.

arxiv3d agoScore 72
large language modelsoptimizationretrieval
Research Editor selected

Observable-Specific Validity Tests for Scientific AI

This paper introduces observable-specific validity records for scientific AI, linking reductions to reference models, error measures, tolerances, parameter domains, and interventions. It demonstrates explicit certificates for a singularly perturbed oscillator and Hubbard dimer relations, and shows that imposing dimensional homogeneity reduces energy scale transfer error from 52.3% to 0.0768% across 16 neural fits. The work also derives an exact fixed control query requirement for mechanism discrimination and provides a 256-task evaluation interface.

Why it matters: Provides a concrete, testable framework for validating scientific AI models, with quantitative results and practical implications for physical transfer and mechanism discrimination.

arxiv3d agoScore 82
scientific AI validationcontrolled approximationphysical transfer
Research

Geo-FSRL: Geometry-Optimized Few-Step Flow Reinforcement Learning

Geo-FSRL introduces a selection principle for stochastic policies in few-step flow models, minimizing conditional KL divergence for velocity-output updates. It derives a closed-form optimizer within a coefficient-preserving family of isotropic Gaussian transitions, improving training stability. The method achieves higher final reward scores than Flow-GRPO and Flow-CPS on image and video generation under 4-step settings.

arxiv3d agoScore 78
few-step flow modelsreinforcement learninggenerative AI
Research

Aligning MLLMs with Human Cognition via Behavior-Derived Semantic Dimensions

Researchers propose a framework to align multimodal large language models with human cognitive structure by using a behavior-derived semantic embedding space of 66 dimensions from 4.7 million human Odd-One-Out judgments. The method infers salient decision dimensions for each triplet and generates dimension-grounded rationales, improving consistency with human similarity judgments and increasing representational alignment in fMRI data. The approach retains competitive performance on standard multimodal benchmarks.

arxiv3d agoScore 78
multimodal large language modelshuman-AI alignmentcognitive science
Research Editor selected

Chronos-2: A Foundation Model for Multivariate Time Series Forecasting

Chronos-2 is a new foundation model for zero-shot forecasting that models interactions among multivariate time series and heterogeneous covariates, unlike prior models that treat series independently. It achieves state-of-the-art accuracy on average, improving skill scores by 5.2 percentage points and win rates by 10 percentage points over strong baselines. The model is computationally efficient, generating forecasts for 100 series in under a second on a mid-range GPU, and matches or surpasses specialized methods in domains like infectious disease, macroeconomics, carbon flux, and runoff.

Why it matters: This introduces a significant advance in time series foundation models, enabling multivariate interaction modeling and broad cross-domain applicability with strong performance and efficiency.

arxiv3d agoScore 85
Chronos-2time series forecastingfoundation models
Research Editor selected

ETAPS: Gradual Pruning with Sparse Adaptation Achieves High Quality at Extreme Sparsity

Researchers propose ETAPS, a pruning method that gradually tightens a global sparsity constraint while training a sparse delta with a small fixed budget. This approach avoids model-sized optimizer states, enabling efficient pruning of LLMs at extreme sparsity levels. Across models from 125M to 13B parameters, ETAPS achieves lower perplexity than the prior state-of-the-art ELSA at sparsities from 50% to 90%, with up to 42% perplexity reduction. It also reduces cost significantly, pruning LLaMA2-7B on a single H200 with 5x smaller persistent state and 49% fewer GPU-hours compared to ELSA.

Why it matters: This paper presents a concrete, recent advancement in LLM pruning that improves both quality and efficiency, offering practical value for deploying large models.

arxiv3d agoScore 85
model compressionlarge language modelsefficient inference
Research

Audit Finds Test-Time Search Gains Limited for World Action Models

A pre-registered audit of test-time scaling in world action models on Cosmos Policy and RoboCasa reveals that learned value selectors underperform random selection, and oracle gains are minimal. Token pruning reduces FLOPs but fails to achieve target speedups, and a silent rendering corruption was identified and fixed. The study emphasizes auditing test-time scaling as a chain of premises rather than relying on success rates alone.

arxiv3d agoScore 78
test-time scalingworld action modelsAI evaluation
Research

ID2Pattern: Pretraining Generalizable Identity Behavior Patterns for Transaction Risk Foundation Models

ID2Pattern is a pretraining framework that captures identity behavior patterns in transaction sequences using a Local Anonymous ID tokenizer and a multi-scale pattern codebook. It outperforms strong baselines on an industrial dataset with over 100M sequences and six public datasets, improving performance by 4.13% and 8.83% on average respectively. The method remains effective even when identity values are unseen during training, showing potential for generalization to new users and markets.

arxiv3d agoScore 78
transaction risk modelingbehavioral pretrainingidentity encoding
Research Editor selected

DAMI: Dual-Axis Memory Initialization Boosts Long-Context Retrieval in Gated Linear Attention

DAMI is a new initialization method for gated linear attention models that configures gate parameters and input activations before training to improve long-context retrieval. It assigns geometric timescales across heads and a low-high-low input-sensitivity profile across layers, calibrated with a small activation sample. Across five model families, DAMI improves RULER-style retrieval accuracy by 5.29 to 16.71 percentage points over random initialization baselines, while keeping language modeling and reasoning performance comparable.

Why it matters: This paper presents a practical, training-free initialization technique that yields significant retrieval gains across multiple state-of-the-art linear attention models, offering immediate value for researchers and practitioners working on long-context AI.

arxiv3d agoScore 82
Gated Linear AttentionLong-Context RetrievalModel Initialization
Research Editor selected

SecPO: Adversarial Training and New Loss Cut Prompt Injection Attack Success Rates Dramatically

Researchers propose SecPO, a principled adversarial training pipeline for defending LLM agents against prompt injection attacks. They introduce a SecPO loss that approximates an idealized injection-invariant reference model, and combine it with efficient synthesis of strong injected inputs. Their SecPO + AT model reduces attack success rates by up to 14.5x compared to Meta-SecAlign, and further 2.4-4.6x over DPO loss, while maintaining utility across nine benchmarks.

Why it matters: This paper presents a concrete, state-of-the-art defense against a critical AI security threat, with significant measured improvements and released resources.

arxiv3d agoScore 85
AI securityprompt injectionadversarial training
Research

AutoAnalysis: Automated Self-Updating Meta-Analysis of Human-AI Collaboration

AutoAnalysis is an automated, self-updating meta-analysis that synthesizes evidence on when humans and AI work better together or alone. Its latest run includes 1,955 effect sizes from 420 papers, finding that human-AI combinations outperform humans alone but underperform the better of either alone. The system integrates new studies as they emerge, providing cumulative evidence across tasks and AI agents.

arxiv3d agoScore 78
human-AI collaborationmeta-analysisAI performance evaluation
Research

TradeWar benchmark evaluates LLM trade negotiations by execution outcomes

Researchers introduced TradeWar, a multi-country simulation benchmark that converts negotiation dialogue into tariff and trade-share policies, applies capacity and network constraints during settlement, and scores outcomes with an Economic Health Index. They also propose TACTIC, an agent that refines negotiation strategy across episodes using prior experience, opponent behavior, and settlement feedback without updating base model weights. In reported results, PromptLLM achieved a 75% agreement rate but a 57.1 final EHI, while TACTIC reached 68.8; across 20 sequential episodes and three seeds, TACTIC improved final EHI from 58.2 to 73.2 versus 65.2 for an ablation without cross-episode updates. TACTIC also showed smaller performance degradation under technology-control and energy-crisis shocks.

arxiv3d agoScore 78
LLM agentsnegotiation benchmarkTradeWar
Research

LLM-SR-UQ: Quantifying Structural Uncertainty in LLM-Guided Symbolic Regression

This paper introduces LLM-SR-UQ, a framework that quantifies uncertainty in LLM-guided symbolic regression by retaining competing equation structures and measuring their disagreement. It addresses the failure of standard conformal intervals under extrapolation, improving coverage attainment while preserving in-distribution performance. The method shows generalizability across other symbolic-regression methods.

arxiv3d agoScore 78
LLM-guided symbolic regressionuncertainty quantificationconformal prediction
Research

Looping Pretrained Models Rarely Pays Off: Study Finds Only Small Models Benefit

A new arXiv study investigates whether adding loops to already-trained models is worth the extra inference compute. Across Qwen3 and Qwen3.5 models from 0.8B to 9B parameters, only the 0.8B looped model outperformed both baselines (equal parameters and equal FLOPs). At 4B and 9B, looped models failed to beat the same model trained without the loop, indicating that post-pretraining loops are only beneficial for small models with a fixed parameter budget.

arxiv3d agoScore 78
model loopinginference computeQwen models
Research Editor selected

Learning Clean Generative Processes from Noisy Measurements

This paper introduces a method to train generative models of clean images using only noisy observations, without ever seeing clean data. It shows that Noise2Noise regression can learn posterior predictions at or above the training noise level, and that imposing a consistency condition uniquely determines the continuation to the clean image distribution for several noise types. Experiments on CIFAR-10, photon-counting microscopy, and synthetic aperture radar demonstrate that the consistency relation repairs the generation process below the noise level, which otherwise deteriorates.

Why it matters: This is a novel theoretical and practical contribution that enables training generative models on noisy data alone, with broad applicability in imaging domains where clean data is unavailable.

arxiv3d agoScore 82
diffusion modelsnoise-robust learningimage generation
Research Editor selected

Audit Finds LLM Health Advice Varies by User Persona, Factual Floor Helps but Not Uniformly

A new arXiv study audits six LLMs from four providers on smoking-cessation advice, finding that responses vary significantly based on user persona. Models mention FDA-approved cessation medications less often to teen personas (by 32–67 percentage points) and often give fewer facts to users claiming healthcare expertise. A system prompt enforcing a factual floor reduced persona differences in all models, but its effect on overall fact coverage varied across models, indicating limited transferability. The authors release all 2,880 responses and analysis code.

Why it matters: This study provides concrete, recent evidence of persona-dependent variation in LLM health advice and tests a practical intervention, offering actionable insights for AI deployment in high-stakes domains.

arxiv3d agoScore 85
LLM behaviorhealth AIfairness
Research

New Newton-type method achieves near-optimal complexity for convex finite-sum optimization under individual smoothness

This paper studies stochastic second-order oracle complexity for smooth convex finite-sum optimization with n components. Under individual smoothness, the authors prove a lower bound of Ω(n + n^{5/7} ε^{-2/7}) and design a Taylor-corrected lazy Newton method with matching upper bound up to logarithmic factors. The result improves on prior work that assumed averaged smoothness.

arxiv3d agoScore 72
optimization theoryconvex optimizationNewton methods