2
Hallo4D: Multi-Modal Hallucination Mitigation for Consistent Spatio-Temporal Generation
Researchers have developed a new method to reduce spatial and temporal hallucinations in 4D generative models by improving geometric consistency.
2
Matilda: Engine-Agnostic Search with Human Policy Guidance
Matilda is a new chess engine architecture that combines search-based methods with human-like neural policies to better model diverse play styles.
2
Real-time fall detection based on vision for low-power edge platforms
Researchers have developed a physics-informed vision system for real-time fall detection optimized for low-power edge computing devices.
2
Demonstrating TOFFEE: A Learned System for Synthesizing Data Agent Trajectories at Scale
Researchers introduced TOFFEE, a system designed to synthesize data agent trajectories to improve performance in complex, heterogeneous enterprise environments.
2
Learning-based Probabilistic Load Forecasting with Post-hoc and In-model Uncertainty
This study evaluates methods for managing input uncertainty in machine learning models used for probabilistic load forecasting in smart buildings.
2
IQA-T1: Tool-based Visual Evidence Reasoning for Image Quality Assessment
The IQA-T1 model improves image quality assessment by incorporating tool-based visual evidence reasoning to overcome the limitations of standard multimodal large language models.
2
Graph-Constrained Policy Learning for Extreme Clinical Code Prediction
This research introduces a graph-constrained policy learning approach to improve the accuracy of clinical code prediction from discharge summaries.
2
A Comparative Analysis of Institutional and Course Generative AI Policies within Higher Education: Implications for Instruction in Computing Education
Researchers compared institutional policies on generative AI in higher education, focusing on the specific challenges faced by computer science departments.
2
Enabling 24-hour Agricultural Robotics: Unsupervised Day-to-Night Cross-Modal Image Translation for Nighttime Visual Navigation
Researchers have proposed an unsupervised image translation method to improve the nighttime navigation capabilities of agricultural robots.
2
ReLope: KL-Regularized LoRA Probes for Multimodal LLM Routing
This paper proposes a regularization technique for probe routing to improve the performance of multimodal large language model systems when balancing cost and accuracy.
2
CANDI: Contextual Alignment for Niche Domains Question Answering
The authors introduce a new benchmark, CANDI-QA, to assess the contextual grounding and domain-specific knowledge of LLMs in fields like finance and medicine.
2
独家丨前英特尔工业团队布局桌面金属CNC，「灵钜创新」获啟赋资本天使轮融资
Startup Lingju Innovation has raised angel funding to develop consumer-grade desktop metal CNC machines integrated with AI control algorithms.
2
Do You Remember? Toward Memory-Centric Multimodal AI
Researchers propose a new architecture called DoYouRemember that enables multimodal large language models to utilize reconstructive memory rather than relying on one-shot processing.
2
Removable Defects: The Economics and Limits of Deliberate Deficiency
Researchers propose a theoretical framework for intentionally maintaining model deficiencies as a design choice that can be bypassed when necessary.
2
Learning to Discretize: Diffusion-Based Adaptive Mesh with Spectral Guidance
Researchers propose a diffusion-based method for learning adaptive meshes to optimize spatial and spectral resolution in neural partial differential equation surrogates.
2
The Computational Basis of Confidence in Large Language Models
This study investigates the computational mechanisms underlying confidence signals in large language models to improve their reliability.
2
Calibration-First Reward-Component Auditing for Reinforcement Learning Control in Smart Greenhouses
The paper proposes a calibration-first reward auditing framework to improve the transparency and interpretability of reinforcement learning policies used in smart greenhouse climate control.
2
Representing and Generating Levels Over Time through Playtrace Reconstructive Partitioning
The authors introduce a novel representation and generation method that captures the dynamic, time-based nature of video game levels using playtrace data.
2
Scale-Aware Attention for Scarce Neural Data: An RG-Flow Transformer on Sleep-EDF EEG
The authors introduce an RG-Flow Transformer that incorporates scale-aware inductive biases to improve neural data analysis in sleep EEG recordings.
2
Multi-Perspective Agentic Program Repair via Code Property Graphs and Temporal Execution Graphs
The CT-Repair framework introduces an agentic approach to automated program repair by integrating static and dynamic code analysis to improve patch generation.
2
Measurement Risk in Supervised Financial NLP: Rubric and Metric Sensitivity on JF-ICR
The study highlights how sensitive financial natural language processing benchmarks are to rubric and metric variations, potentially impacting model selection in financial applications.
2
Attention-Discounted Adaptive Sampler for Masked Diffusion Language Models
Researchers have proposed a new sampling method for masked diffusion language models to improve token generation stability by addressing prediction coupling.
2
Follow the Latent Roadmap: Navigating Revocable Decoding for Diffusion LLMs with Anchor Tokens
This paper introduces a decoding strategy for diffusion language models designed to reduce error propagation and improve generation quality.
2
Generalized Distribution-Free Semi-Supervised Learning with Risk Rewrite
The paper proposes a generalized framework for semi-supervised learning that avoids reliance on specific distributional assumptions.