6292 papers
This study evaluates the ability of six LLM-based systems to answer expert-level questions about high-temperature superconductivity using a curated database of 1,726 papers, finding that retrieval-augmented generation (RAG) systems outperform closed models in providing comprehensive, well-supported answers while highlighting both the potential and current limitations of LLMs in specialized scientific domains.
This paper introduces DeepEyesV2, an agentic multimodal model that employs a two-stage training pipeline combining cold-start data curation and reinforcement learning to effectively integrate external tools like code execution and web search for complex real-world reasoning tasks.
The paper introduces "What We Don't C," a novel latent flow matching approach that disentangles latent subspaces by explicitly removing information from conditional guidance to generate meaningful residual representations, thereby enabling the discovery and analysis of factors of variation not captured in the conditioning variables.
The paper proposes D-GAP, a dataset-agnostic and gradient-guided augmentation method that adaptively blends frequency amplitudes and pixel values to reduce domain-specific learning biases and restore spatial details, thereby significantly improving out-of-domain robustness in computer vision models.
This paper introduces STREAM-VAE, a dual-path variational autoencoder that separates slow drifts and fast spikes in vehicle telemetry data to overcome the limitations of standard reconstruction-based methods and achieve robust anomaly detection across diverse operating modes.
This paper introduces REMSA, a constraint-aware agent built upon the newly constructed RSFM Database (RS-FMD) that automates the selection of suitable remote sensing foundation models from natural language queries by integrating structured metadata retrieval with task-driven decision workflows, achieving superior performance over baselines in a novel expert-verified benchmark.
This paper proposes a hierarchical dual-strategy framework that achieves precise selective unlearning of privacy-sensitive medical knowledge in large language models while preserving fundamental competencies, demonstrated by high forgetting and preservation rates on clinical datasets with minimal parameter modification.
This paper introduces CostNav, the first physics-grounded navigation benchmark that evaluates autonomous agents using real-world economic data to reveal that current methods, despite varying in hardware and architecture, all fail to achieve economic viability due to negative contribution margins.
This paper introduces IndiMathBench, a human-verified benchmark of 312 formal Lean 4 theorems derived from Indian Mathematics Olympiads, which utilizes an AI-powered human-assisted pipeline to address the scarcity of high-quality training data and reveals significant challenges in current autoformalization and theorem proving capabilities.
This paper proposes C3, a novel uncertainty quantification method that trains controllable video models to generate high-resolution, calibrated confidence heatmaps at the subpatch level by estimating uncertainty in latent space and using strictly proper scoring rules, thereby enabling reliable hallucination detection and out-of-distribution identification for robotics applications.
The paper introduces Trio, a closed-loop molecular generation framework that integrates fragment-based language modeling, reinforcement learning, and Monte Carlo tree search to produce chemically valid, diverse, and pharmacologically optimized ligands with significantly improved binding affinity, drug-likeness, and synthetic accessibility compared to state-of-the-art methods.
This paper introduces computationally efficient and statistically consistent Random Forest variants that minimize the maximum risk across diverse environments to improve out-of-distribution generalization, offering novel guarantees for mean squared error, negative reward, and regret-based risks.
GTR-Turbo is a highly efficient training method for multi-modal agents that eliminates the need for costly external teacher models by using merged checkpoints from ongoing reinforcement learning as a "free" teacher, thereby improving accuracy by 10–30% while reducing training time and compute costs by 50% and 60%, respectively.
This paper introduces the Pretrained Battery Transformer (PBT), a foundation model that leverages battery-knowledge-encoded mixture-of-experts layers to overcome data scarcity and heterogeneity, achieving state-of-the-art universal battery life prediction across diverse chemistries and conditions.
This paper presents a framework using YOLOv8 and Finer-CAM to achieve 96% accuracy in classifying seven European tree species from TLS 3D point clouds while demonstrating that the model's decisions are interpretable and primarily rely on crown features for most species, with stems playing a more significant role for others.
This paper introduces "Bayesian wind tunnels" to rigorously demonstrate that small transformers perform exact Bayesian inference through a specific geometric mechanism involving residual streams as belief substrates and attention-based routing, a capability that capacity-matched MLPs fundamentally lack.
This paper provides a first-order analysis demonstrating that cross-entropy training in transformers induces a coupled specialization of attention routing and value updates—functioning as a two-timescale EM procedure—that sculpts low-dimensional Bayesian manifolds, thereby explaining how gradient-based optimization enables precise probabilistic reasoning.
This paper demonstrates that production-grade language models preserve a low-dimensional geometric substrate, specifically an entropy-aligned axis in their last-layer value representations, which encodes Bayesian posterior structures and serves as a privileged readout for uncertainty, even though it is not a singular computational bottleneck for inference.
This paper systematically evaluates the phenomenon of "over-searching" in search-augmented large language models, where unnecessary tool invocation harms efficiency and accuracy, and proposes the Tokens Per Correctness (TPC) metric along with mitigation strategies to address this issue.
This paper proposes a Secure Multi-Tenant Architecture (SMTA) combined with a novel Burn-After-Use (BAU) mechanism to effectively prevent data leakage in enterprise LLMs by enforcing strict instance isolation and ephemeral context destruction, achieving high defense success rates against both semantic leakage attacks and post-session persistence threats in experimental evaluations.