arXiv AI
Jun 11
Soft-Prompt Tuning for Fair and Efficient LLM Benchmark Evaluation
arXiv:2606. 12117v1 Announce Type: cross Abstract: Benchmark scores often misrepresent a large language model's (LLM's) knowledge, because they rely, e.
Benchmarks and evaluation
Leaderboards, eval harnesses and ablations — the contested business of deciding which model is actually better.
arXiv AI
Jun 11
MARIC: Multi-Agent Reasoning for Image Classification
arXiv:2509. 14860v2 Announce Type: replace-cross Abstract: Image classification has traditionally relied on parameter-intensive model training, requiring large-scale annotated datasets and extensive fine tuning to achieve competitive performance.
arXiv AI
Jun 11
Multi-View In-Cabin Monitoring System for Public Transport Vehicles
arXiv:2606. 11739v1 Announce Type: cross Abstract: We introduce a multi-view in-cabin monitoring dataset for public transportation with synchronized RGB and depth images from four inward-facing cameras and a rotating LiDAR covering the vehicle interior of a digitalized and partly automated German city bus.
arXiv AI
Jun 11
Lung-SRAD: Spectral-Aware Regularized Audio DASS with Dual-Axis Patch-Mix Contrastive Learning for Respiratory Sound Classification
arXiv:2606. 11922v1 Announce Type: cross Abstract: Recent respiratory sound classification (RSC) studies largely rely on CLS-token driven self-attention architectures such as the Audio Spectrogram Transformer (AST).
arXiv AI
Jun 11
Metadata-Aware Multi-Prompt Reasoning for Zero-Shot Accident Understanding
arXiv:2606. 12047v1 Announce Type: cross Abstract: In this paper, we address the problem of zero-shot understanding of accidents from surveillance videos by identifying when an impact event occurs, what type of impact it is, and where in the frame it occurs using natural language.
arXiv AI
Jun 11
MODF-SIR: A Multi-agent Omni-modal Distilled Framework for Social Intelligence Reasoning
arXiv:2606. 12018v1 Announce Type: new Abstract: We propose a multi-agent collaborative framework built upon a lightweight Multimodal Large Language Model (MLLM), specifically designed for social intelligence reasoning.
arXiv AI
Jun 11
TAROT: Task-Adaptive Refinement of LLM-prior Graphs for Few-shot Tabular Learning
arXiv:2606. 11640v1 Announce Type: cross Abstract: Few-shot tabular learning provides a cost-effective approach for real-world applications where annotation is costly and collecting sufficient samples for new tasks is difficult.
arXiv AI
Jun 11
Toward Trustworthy AI: Multi-Target Adversarial Attacks and Robust Defenses for Continuous Data Summarization
arXiv:2606. 11804v1 Announce Type: new Abstract: Trustworthy AI requires reliable data-processing pipelines, not only robust downstream predictive models.
arXiv Machine Learning
Jun 11
PCS-UQ: Uncertainty Quantification via the Predictability-Computability-Stability Framework
arXiv:2505. 08784v2 Announce Type: replace-cross Abstract: As machine learning (ML) enters high-stakes domains, trustworthy uncertainty quantification (UQ) is essential for safety.
arXiv AI
Jun 11
On the Limits of LLM-as-Judge for Scientific Novelty Assessment
arXiv:2606. 12071v1 Announce Type: cross Abstract: LLMs are increasingly used to generate and judge scientific ideas.
arXiv AI
Jun 11
Latent World Recovery for Multimodal Learning with Missing Modalities
arXiv:2606. 12362v1 Announce Type: cross Abstract: We study multimodal learning under missing modalities, with particular motivation from bioscience applications in which heterogeneous modalities are often only partially available when decisions need to be made.
arXiv AI
Jun 11
Semantic search for 100M+ galaxy images using AI-generated captions
arXiv:2512. 11982v2 Announce Type: replace-cross Abstract: Finding scientifically interesting phenomena through slow manual labeling campaigns severely limits our ability to explore the billions of galaxy images produced by telescopes.
arXiv AI
Jun 11
TokenRatio: Principled Token-Level Preference Optimization via Ratio Matching
arXiv:2605. 12288v3 Announce Type: replace-cross Abstract: Direct Preference Optimization (DPO) is a widely used RL-free method for aligning language models from pairwise preferences, but it models preferences over full sequences even though generation is driven by per-token decisions.
arXiv AI
Jun 11
Towards Deep Learning Surrogate for the Forward Problem in Electrocardiology: A Scalable Alternative to Physics-Based Models
arXiv:2512. 13765v2 Announce Type: replace-cross Abstract: The forward problem in electrocardiology, computing body surface potentials from cardiac electrical activity, is traditionally solved using physics-based models such as the bidomain or monodomain equations.
arXiv Machine Learning
Jun 11
On the Stability of Growth in Structural Plasticity
arXiv:2605. 15435v2 Announce Type: replace Abstract: Standard deep-learning pipelines usually choose the network architecture before training and keep it fixed throughout optimization.
arXiv AI
Jun 11
FlowBank: Query-Adaptive Agentic Workflows Optimization through Precompute-and-Reuse
arXiv:2606. 11290v1 Announce Type: cross Abstract: Large Language Model (LLM)-based multi-agent systems are increasingly powerful, but current agentic workflow optimization paradigms make an unsatisfying trade-off.
arXiv AI
Jun 11
MSUE: Multi-Modal Soccer Understanding Expert
arXiv:2606. 12106v1 Announce Type: cross Abstract: This paper presents our solution to the 2026 SoccerNet VQA Challenge.
arXiv AI
Jun 11
GPO: Learning from Critical Steps to Improve LLM Reasoning
arXiv:2509. 16456v3 Announce Type: replace Abstract: Large language models (LLMs) are increasingly used in various domains, showing impressive potential on different tasks.
arXiv AI
Jun 11
Reason, Then Re-reason: Cross-view Revisiting Improves Spatial Reasoning
arXiv:2606. 11683v1 Announce Type: cross Abstract: Spatial reasoning from egocentric videos is inherently challenging because the observable evidence is constrained by the camera trajectory.
arXiv AI
Jun 11
From Uniform to Learned Graph Priors: Diffusion for Structure Discovery
arXiv:2606. 11831v1 Announce Type: cross Abstract: Neural relational inference (NRI) methods discover interaction graphs from trajectories through variational reasoning on discrete potential edges.