HatePrototypes: Interpretable representations for hate speech detection covering implicit and explicit hate. Addresses content moderation with transferable embeddings.
UnfoldLDM combines deep unfolding networks with latent diffusion models for blind image restoration. Model-based interpretable approach to image processing.
Probabilistic certification framework improving SmoothLLM defense against LLM jailbreaking attacks. Addresses robustness guarantees with realistic assumptions.
Yo'City: Agentic framework using self-critic expansion for personalized, boundless 3D city generation. Demonstrates AI agent reasoning in creative generation tasks.
Transformer model with physics-inspired attention masks for neutrino reconstruction in KM3NeT/ORCA telescope. Domain-specific deep learning application.
Automated pipeline for generating multi-turn conversational jailbreak attacks against LLMs using psychological principles like FITD without manual dataset creation.
Contrastive learning approach for adapting foundation models to domain-specific tasks in Earth observation without full retraining.
Protein inverse folding method combining retrieval-augmented approaches with denoising diffusion for amino acid sequence design from protein structures.
Deep learning pipeline for automated foraminifera species classification from micro-CT scans using a dataset of 27 species across 12 representative classes.
AltNet addresses plasticity loss in RL-trained neural networks via parameter reset strategies. Research on continual learning for RL agents.
arXiv paper on evaluating agentic systems via process-centric analysis of trajectories and reasoning patterns rather than outcomes alone. Foundational agent analysis framework.
Shapley value extension for nonlinear feature attribution and explainability. XAI research not specific to LLMs or agents.
Deep learning method for off-road vector extraction from geospatial data. Computer vision research unrelated to user interests.
SALVE framework for neural network interpretability and control using sparse autoencoders. Mechanistic interpretability research not focused on LLMs or agents.
LaMer: Meta-RL framework enabling LLM agents to actively explore and learn from trial-and-error in multi-turn tasks. Research on agent training methodology.
Test-time depth refinement framework combining depth estimation with diffusion models. Computer vision research unrelated to user interests.
arXiv paper analyzing cost trade-offs between reasoning and non-reasoning LLMs for Text-to-SQL tasks on cloud platforms. Empirical efficiency comparison.
DrivingGen benchmark for generative video world models in autonomous driving. Research on agent simulation and synthetic data generation.
NC-Bench: arXiv benchmark evaluating LLM conversational competence on form/structure vs content. Research paper on LLM evaluation methodology.
Audit of LAION-Aesthetics Predictor studying whose aesthetic values are embedded in visual generative AI training datasets.
POI recommendation system using hypergraph learning to capture mobility variations across contextual scenarios in location-based social networks.
Benchmark with 1,800 code completion instances across 6 languages derived from real developer telemetry; avoids contamination, enables detailed diagnostics.
FPGA-based CNN inference architecture with continuous data flow for low-latency, high-throughput deep learning deployment.
Training-free caching framework for Flow Matching inference using average-velocity perspective and Jacobian-vector products for acceleration.
Open-source cybersecurity LLM trained on 11.8B tokens of curated domain data; supports diverse security workflows while protecting sensitive data.
Bitcoin price prediction applying Combinatorial Fusion Analysis to ensemble multiple ML models for improved robustness.
Stock price prediction using LLM-based sentiment analysis on news; evaluates benefit of sentiment features versus prediction methods separately.
Data Shapley attribution method for adaptive optimizers like Adam, extending in-run attribution beyond SGD's linear structure.
Multi-label classification study using Schwartz value hierarchies for sentence-level human value detection on sparse, imbalanced datasets.
Reward shaping method for LLM reasoning via reinforcement learning, addressing entropy collapse and exploration challenges in verification-based training.
Study of recurring vulnerabilities in LLM-generated code; introduces FSTab for black-box attacks predicting backend security issues from frontend patterns.
Semantic search system over 9M mathematical theorems using embeddings to retrieve specific results for mathematicians and theorem-proving agents.
LLM-driven recommendation system using multimodal motivation modeling to improve content preference prediction by incorporating review text and heterogeneous data.
Diffusion-guided pretraining for brain graph foundation models, using learnable augmentation for connectome data instead of random dropping.
CoCoA decoder mitigates LLM hallucinations by detecting representational instability across layers, requiring no training.
SToRM token reduction technique optimizes multimodal LLMs for end-to-end autonomous driving with natural language interaction.
Uses agent guidance from learned policies to accelerate robotic RL, reducing sample inefficiency without 1:1 human supervision.
TrasMuon optimizer improves Muon-style methods by adding trust-region adaptive scaling for robust gradient updates.
Mean velocity policy for one-step action generation in RL, balancing expressiveness and computational efficiency of flow-based policies.
Variational flow-matching framework for simulation-based inference with structured domain constraints on posteriors.
Token-level noise filtering method for LLM fine-tuning datasets, addressing mismatch between sentence-level annotation and token optimization.
LongAudio-RAG hybrid framework for QA over multi-hour audio with temporal grounding and minimal hallucination.
CogitoRAG framework simulates human cognitive memory for retrieval-augmented generation, using semantic diffusion to preserve integrity.
Symmetry-driven deep learning for crystal structure prediction from composition, advancing materials discovery.
Condition-gated reasoning system for biomedical QA that handles patient-specific conditional logic in clinical decision-making.
Analyzes deployment tradeoffs in conformal predictors beyond coverage, examining commit vs defer vs error exposure operational metrics.
CrystaL enables latent chain-of-thought reasoning in multimodal LLMs without predefined supervision, improving vision-language integration.
ModernBERT-based multilingual encoder family (150M-300M params) pretrained on 35 languages with domain and dimensional adaptation.
Continual multi-task training framework for universal audio representation across speech, environmental sounds, and music.
Deep learning framework for automated refinement of protein structures using cryo-EM density maps with diffusion models.