Mini toolsPapers
Filter by company
-
Catching rationalization in the act: detecting motivated reasoning before and after CoT via activation probing
-
CODMAS: A Dialectic Multi-Agent Collaborative Framework for Structured RTL Optimization
-
OPERA: Online Data Pruning for Efficient Retrieval Model Adaptation
-
SYMDIREC: A Neuro-Symbolic Divide-Retrieve-Conquer Framework for Enhanced RTL Synthesis and Summarization
-
A scalable neural bundle map for multiphysics prediction in lithium-ion battery across varying configurations
-
Adaptive Contracts for Cost-Effective AI Delegation
-
An FPGA-Based SoC Architecture with a RISC-V Controller for Energy-Efficient Temporal-Coding Spiking Neural Networks
-
AI Scientist via Synthetic Task Scaling
-
Anonymous-by-Construction: An LLM-Driven Framework for Privacy-Preserving Text
-
Alignment Makes Language Models Normative, Not Descriptive
-
SA-CycleGAN-2.5D: Self-Attention CycleGAN with Tri-Planar Context for Multi-Site MRI Harmonization
-
TharuChat: Bootstrapping Large Language Models for a Low-Resource Language via Synthetic Data and Human Validation
-
Single-Pass Discrete Diffusion Predicts High-Affinity Peptide Binders at >1,000 Sequences per Second across 150 Receptor Targets
-
Towards Solving Polynomial-Objective Integer Programming with Hypergraph Neural Networks
-
Modeling Matches as Language: A Generative Transformer Approach for Counterfactual Player Valuation in Football
-
Tracking the Discriminative Axis: Dual Prototypes for Test-Time OOD Detection Under Covariate Shift
-
Towards Foundation Models for Consensus Rank Aggregation
-
InterPol: De-anonymizing LM Arena via Interpolated Preference Learning
-
ADV-0: Closed-Loop Min-Max Adversarial Training for Long-Tail Robustness in Autonomous Driving
-
Bidirectional Chinese and English Passive Sentences Dataset for Machine Translation
-
SCAN: Sparse Circuit Anchor Interpretable Neuron for Lifelong Knowledge Editing
-
HYDRA: Unifying Multi-modal Generation and Understanding via Representation-Harmonized Tokenization
-
Decomposing Probabilistic Scores: Reliability, Information Loss and Uncertainty
-
Multi-turn Physics-informed Vision-language Model for Physics-grounded Anomaly Detection
-
Why the Valuable Capabilities of LLMs Are Precisely the Unexplainable Ones
-
A proof-of-concept for automated AI-driven stellarator coil optimization with in-the-loop finite-element calculations
-
Practicing with Language Models Cultivates Human Empathic Communication
-
Mechanistic Foundations of Goal-Directed Control
-
In-Context Symbolic Regression for Robustness-Improved Kolmogorov-Arnold Networks
-
HalDec-Bench: Benchmarking Hallucination Detector in Image Captioning
-
SAGE: Multi-Agent Self-Evolution for LLM Reasoning
-
SEMAG: Self-Evolutionary Multi-Agent Code Generation
-
Directional Embedding Smoothing for Robust Vision Language Models
-
AGCD: Agent-Guided Cross-Modal Decoding for Weather Forecasting
-
Probe-then-Plan: Environment-Aware Planning for Industrial E-commerce Search
-
IConE: Batch Independent Collapse Prevention for Self-Supervised Representation Learning
-
Automatic Termination Strategy of Inelastic Neutron-scattering Measurement Using Bayesian Optimization for Bin-width Selection
-
Mastering the Minority: An Uncertainty-guided Multi-Expert Framework for Challenging-tailed Sequence Learning
-
Exemplar Diffusion: Improving Medical Object Detection with Opportunistic Labels
-
Self-Supervised ImageNet Representations for In Vivo Confocal Microscopy: Tortuosity Grading without Segmentation Maps
-
From Documents to Spans: Code-Centric Learning for LLM-based ICD Coding
-
Flash-Unified: A Training-Free and Task-Aware Acceleration Framework for Native Unified Models
-
Dataset Diversity Metrics and Impact on Classification Models
-
Faster Inference of Flow-Based Generative Models via Improved Data-Noise Coupling
-
Advancing Multimodal Agent Reasoning with Long-Term Neuro-Symbolic Memory
-
Survey of Various Fuzzy and Uncertain Decision-Making Methods
-
Algorithms for Deciding the Safety of States in Fully Observable Non-deterministic Problems: Technical Report
-
Evaluating the Robustness of Reinforcement Learning based Adaptive Traffic Signal Control
-
Scalable Simulation-Based Model Inference with Test-Time Complexity Control
-
Datasets for Verb Alternations across Languages: BLM Templates and Data Augmentation Strategies
