arXiv Machine Learning
Aug 18
Learning Auditable Classifier Models: Source-Disjoint Tree Ensembles
arXiv:2608. 15725v1 Announce Type: new Abstract: Predictive models in clinical and regulated settings must be accurate and fully auditable.
Benchmarks and evaluation
Leaderboards, eval harnesses and ablations — the contested business of deciding which model is actually better.
arXiv Machine Learning
Aug 18
Geometry of Forgetting: Representation Flux in Continual Learning
arXiv:2608. 15854v1 Announce Type: new Abstract: Catastrophic forgetting remains a fundamental obstacle to continual learning, where neural networks lose previously acquired knowledge while learning new tasks.
arXiv Machine Learning
Aug 18
Retrieval-guided Twin Fusion with Similarity-aware Contrast for Molecule-Text Alignment
arXiv:2608. 16005v1 Announce Type: new Abstract: This paper studies the problem of molecule-text alignment, which aims to project molecules and their textual descriptions into a joint latent space for downstream tasks including molecule search and molecular property prediction.
arXiv Machine Learning
Aug 18
Transfer Learning of Keystroke Dynamics for Cross-Device User Authentication
arXiv:2608. 16334v1 Announce Type: new Abstract: Keystroke dynamics (typing patterns) can be used as a behavioural biometric modality for user authentication, with applications such as fraud prevention.
arXiv AI
Aug 18
LongRCA Bench: Diagnosing Responsible Roles and Root Causes in Long-Horizon Agent Failures
arXiv:2608. 15242v1 Announce Type: new Abstract: When a long-horizon agent execution fails, outcome-level evaluation reveals the unsuccessful result but not where the decisive error entered the trajectory.
arXiv AI
Aug 18
ATLAS: Scaffold-Free Algorithm Synthesis by LLMs via Embedding-Guided Quality-Diversity Search
ATLAS is an embedding‑guided quality‑diversity framework that enables scaffold‑free synthesis of full algorithms for combinatorial optimization using large language models. It allows the LLM to freely choose, restructure, and control algorithm components while automatically detecting and repairing execution, interface, and feasibility failures. Across four NP‑hard problems, ATLAS outperforms state‑of‑the‑art component‑synthesis methods and remains competitive with strong human‑designed algorithms, demonstrating that a larger design space can be practically searched.
arXiv Machine Learning
Aug 18
EquiPocket: an E(3)-Equivariant Geometric Graph Neural Network for Ligand Binding Site Prediction
EquiPocket is an E(3)-equivariant Graph Neural Network designed to predict ligand binding sites on proteins. It processes proteins as geometric graphs, extracting local surface atom geometry, modeling chemical and spatial relationships, and performing equivariant message passing to capture surface geometry. A dense attention output layer mitigates issues caused by variable protein sizes, and experiments show the method outperforms current state‑of‑the‑art approaches.
arXiv AI
Aug 18
GRIP: Grounded Reasoning via Information-Restricted Premises
GRIP (Grounded Reasoning via Information-Restricted Premises) addresses the query dominance problem in retrieval-augmented generation by enforcing a capacity asymmetry: the decoder retains full access to the query while retrieved evidence is funneled through a severe stochastic bottleneck. This design forces the evidence channel to encode only residual information not present in the query. On five reasoning benchmarks, GRIP surpasses strong iterative baselines, reduces query–latent mutual information by about 30×, cuts hallucination by 73%, and its bottleneck outputs occupy subspaces less aligned with the query than baseline representations.
arXiv AI
Aug 18
From Sequence to Structure: Relational Uncertainty Propagation for LLM Agents
The paper introduces RUPA, a trajectory‑level uncertainty quantification framework for large language model agents. RUPA models an agent’s execution as a directed graph of reasoning states, tool interactions, and environment feedback, then propagates uncertainty across this graph to capture long‑range dependencies. Experiments on benchmarks such as τ‑2, Terminal‑Bench‑2, and GAIA show that RUPA outperforms existing methods, enabling earlier failure detection and more reliable agent execution.
arXiv Machine Learning
Aug 18
AMPLIFAI: A Multiphase CT Dataset for Benchmarking Clinical Reasoning in LI-RADS Assessment of Liver Lesions
The paper introduces AMPLIFAI, the first public dataset of multiphase abdominal CT scans annotated with LI-RADS categories and segmented for three key LI-RADS features: arterial phase hyperenhancement, washout, and enhancing capsule. It outlines the dataset’s composition, curation process, and annotation pipeline following the Datasheets for Datasets format to promote transparency and reproducibility. The dataset aims to support the development of AI models for automated hepatocellular carcinoma diagnosis using the biopsy‑free, imaging‑based LI‑RADs framework.
arXiv AI
Aug 18
When Is Shallow Enough? Adaptive Split Federated Learning with Client-Specific Sufficiency Estimation
arXiv:2608. 15639v1 Announce Type: cross Abstract: \textit{Split Federated Learning} (SFL) enables distributed model training by splitting networks between the server and clients.
arXiv AI
Aug 18
Agentic-SQL Revisited: Autonomy-Based Taxonomy and Empirical Benchmark Analysis for LLM Text-to-SQL
arXiv:2608. 15389v1 Announce Type: new Abstract: LLM-based Text-to-SQL progress is reported across heterogeneous benchmarks, backbones, and inference protocols, making cross-system comparison fragile.
Hugging Face Trending Papers
Aug 18
SignalReasoner: Assessing the Upper Bound of 3B Models for Signal Mathematical Reasoning
Post-training with supervised chain-of-thought fine-tuning and reinforcement learning from verifiable rewards has substantially improved the mathematical reasoning capabilities of large language models (LLMs). However, their application to signal processing problems remains relatively under-explored.
Hugging Face Trending Papers
Aug 18
LiveHouse-TS: An Open-world Living Benchmark for Time Series Foundation Models
Time Series Foundation Models (TSFMs) have recently emerged as a highly promising paradigm for cross-domain zero-shot forecasting. However, existing evaluation protocols predominantly rely on static benchmarks with fixed historical test windows.
Hugging Face Trending Papers
Aug 18
Beyond MSE: Rethinking the Evaluation Metric and Benchmarking for Irregular Time Series Forecasting
Existing research on irregular time-series forecasting has primarily focused on model design, while evaluation metrics remain insufficiently studied. Existing benchmarks typically use mean squared error (MSE) as the evaluation metric.
Hugging Face Trending Papers
Aug 17
SCENARIODIFF: A Scenario-level Guidance Framework for Multimodal Time Series Forecasting--Extended Version
Textual context such as news, reports, and logs can provide valuable signals for time series forecasting, especially when future dynamics are driven by external events that are not yet visible in hist...
Hugging Face Trending Papers
Aug 17
Deep Learning for Cross-Border Electricity Price Forecasting: A Comparative Study
While publicly available electricity market data presents a valuable resource for forecasting research, the field lacks established benchmark datasets for standardized comparison. As a result, many st...
Hugging Face Trending Papers
Aug 17
Don't Drop the BATON: Long-Horizon Robot Manipulation via Agentic Subtask Exploration and Transition-aware Memory
Long-horizon robot manipulation chains many contact-rich skills into one multi-stage task. Vision-language-action (VLA) models increasingly master the individual skills, yet the chain still fails: err...
Hugging Face Trending Papers
Aug 17
Diagnosing Dense Same-Class Attribute Misbinding in Large Vision-Language Models
Large vision-language models can recognize the objects and attributes in a crowded scene yet assign an attribute to the wrong same-class instance. Generic visual-question-answering accuracy marks the...
Hugging Face Trending Papers
Aug 17
PixRestore: Unified Image Restoration via Pixel Diffusion Transformer
Unified image restoration (UIR) aims to recover high-quality (HQ) content from low-quality (LQ) images with different degradations using a single model. Most recent methods adapt large pretrained text-to-image (T2I) latent diffusion models for their strong capacity and generative priors.