4/21/2026
Finding Culture-Sensitive Neurons in Vision-Language Models
Study identifying culture-sensitive neurons in vision-language models that preferentially activate for culturally grounded inputs and visual reasoning.
4/21/2026
FlexiCache: Leveraging Temporal Stability of Attention Heads for Efficient KV Cache Management
FlexiCache: KV cache management technique exploiting temporal stability of attention heads to reduce memory overhead in long-context LLM serving.
4/21/2026
In Situ Training of Implicit Neural Compressors for Scientific Simulations via Sketch-Based Regularization
In situ training protocol for implicit neural compressors using sketch-based regularization to prevent catastrophic forgetting in scientific simulations.
4/21/2026
ConMeZO: Adaptive Descent-Direction Sampling for Gradient-Free Finetuning of Large Language Models
ConMeZO: Zeroth-order optimizer for gradient-free LLM finetuning using adaptive descent-direction sampling, reducing memory overhead and convergence time.
4/21/2026
Preparation of Fractal-Inspired Computational Architectures for Automated Neural Design Exploration
FractalNet: Framework generating 1,200+ neural network variants systematically through permutations for automated architecture search and LLM analysis.
4/21/2026
Empowering Multi-Turn Tool-Integrated Agentic Reasoning with Group Turn Policy Optimization
Group Turn Policy Optimization: RL training method for multi-turn tool-integrated reasoning in LLMs with fine-grained turn-level rewards improving agentic performance.
4/21/2026
DeepThinkVLA: Enhancing Reasoning Capability of Vision-Language-Action Models
DeepThinkVLA: Framework identifying necessary conditions for chain-of-thought reasoning to improve vision-language-action robot models through systematic analysis.
4/21/2026
Inference-Time Distillation: Cost-Efficient Agents Without Fine-Tuning or Manual Prompt Engineering
Inference-time distillation enables cost-efficient LLM agents without fine-tuning or prompt engineering, preserving iteration agility for batch jobs.
4/21/2026
Joint Distillation for Fast Likelihood Evaluation and Sampling in Flow-based Models
Joint distillation technique accelerating likelihood evaluation and sampling in flow-based generative models by reducing neural function evaluations.
4/21/2026
DFedReweighting: A Unified Framework for Objective-Oriented Reweighting in Decentralized Federated Learning
DFedReweighting: Framework for objective-oriented reweighting in decentralized federated learning addressing fairness and Byzantine robustness challenges.
4/21/2026
Torch Geometric Pool: the PyTorch library for pooling in Graph Neural Networks
Torch Geometric Pool: PyTorch library standardizing graph pooling methods with unified SRCL interface for easier comparison and reuse across different pooling approaches.
4/21/2026
A Unification of Discrete, Gaussian, and Simplicial Diffusion
Unified framework connecting discrete, Gaussian, and simplicial diffusion models for sequences like DNA, proteins, and language.
4/21/2026
Missing Pattern Tree based Decision Grouping and Ensemble for Enhancing Pair Utilization in Deep Incomplete Multi-View Clustering
Incomplete multi-view clustering method using Missing Pattern Trees to improve pair utilization across inconsistent missing patterns.
4/21/2026
Inter-Agent Relative Representations for Multi-Agent Option Discovery
Multi-agent option discovery method using inter-agent relative representations to improve coordination and reduce joint state space complexity.
4/21/2026
Revisiting Forest Proximities via Sparse Leaf-Incidence Kernels
Forest proximity computation via Separable Weighted Leaf-Collision kernels for improved scalability in kernel and representation-learning pipelines.
4/21/2026
FOREVER: Forgetting Curve-Inspired Memory Replay for Language Model Continual Learning
FOREVER: Forgetting curve-inspired memory replay method for continual learning in large language models.
4/21/2026
Stable On-Policy Distillation through Adaptive Target Reformulation
Adaptive target reformulation approach reducing training instability in on-policy knowledge distillation for language models.
4/21/2026
Geometric Stability: The Missing Axis of Representations
Geometric stability framework for measuring robustness of neural network representations.
4/21/2026
Counterfactual Modeling with Fine-Tuned LLMs for Health Intervention Design and Sensor Data Augmentation
Counterfactual explanation generation using fine-tuned LLMs for health intervention design and sensor data augmentation.
4/21/2026
Robust Tool Use via Fission-GRPO: Learning to Recover from Execution Errors
Fission-GRPO: Reinforcement learning method teaching LLMs to recover from tool execution errors in multi-turn interactions.
4/21/2026
Rethinking Cross-Modal Fine-Tuning: Optimizing the Interaction Between Feature Alignment and Target Fitting
Cross-modal fine-tuning optimization technique balancing feature alignment and target fitting for pre-trained models.
4/21/2026
Less Noise, More Voice: Reinforcement Learning for Reasoning via Instruction Purification
Instruction purification method for improving reinforcement learning efficiency in LLM reasoning tasks.
4/21/2026
Rate-Distortion Optimization for Transformer Inference
Rate-distortion framework for lossy compression of transformer intermediate representations during inference.
4/21/2026
Putting a Face to Forgetting: Continual Learning meets Mechanistic Interpretability
Research on catastrophic forgetting in continual learning using mechanistic interpretability framework.
4/21/2026
UniComp: A Unified Evaluation of Large Language Model Compression via Pruning, Quantization and Distillation
UniComp unified framework evaluating LLM compression via pruning, quantization, and distillation across performance, reliability, and efficiency dimensions.
4/21/2026
MerLin: A Discovery Engine for Photonic and Hybrid Quantum Machine Learning
Open-source discovery engine for photonic and hybrid quantum machine learning with optimized simulation and model evaluation framework.
4/21/2026
SpiralFormer: Looped Transformers Can Learn Hierarchical Dependencies via Multi-Resolution Recursion
Recursive transformer architecture with multi-resolution mechanisms for learning hierarchical dependencies via looped parameter sharing.
4/21/2026
MASPO: Unifying Gradient Utilization, Probability Mass, and Signal Reliability for Robust and Sample-Efficient LLM Reasoning
MASPO algorithm for LLM reasoning combining gradient utilization, probability mass, and signal reliability to replace rigid trust region mechanisms in RLVR.
4/21/2026
Knowledge without Wisdom: Measuring Misalignment between LLMs and Intended Impact
Study measuring misalignment between LLM benchmark performance and real-world impact on downstream educational tasks across multiple models.
4/21/2026
Temporal Representations for Exploration: Learning Complex Exploratory Behavior without Extrinsic Rewards
RL exploration method using temporal representations to learn environment models without extrinsic rewards or tracking novelty directly.
4/21/2026
An LLM-Guided Query-Aware Inference System for GNN Models on Large Knowledge Graphs
Query-aware GNN inference system guided by LLMs for efficient computation on large knowledge graphs with variable complexity queries.
4/21/2026
Differential Privacy in Two-Layer Networks: How DP-SGD Harms Fairness and Robustness
Theoretical analysis of how differential privacy in neural networks affects fairness and adversarial robustness via feature-centric framework.
4/21/2026
Countdown-Code: A Testbed for Studying The Emergence and Generalization of Reward Hacking in RLVR
Countdown-Code benchmark environment for measuring reward hacking in LLMs with verifiable rewards, enabling clear distinction between task solving and reward manipulation.
4/21/2026
From $\log \pi$ to $\pi$: Taming Divergence in Soft Clipping via Bilateral Decoupled Decay of Probability Gradient Weight
Bilateral decoupled decay method for soft clipping in LLM reasoning with verifiable rewards, addressing gradient divergence in GRPO-style optimization.
4/21/2026
LLM as Graph Kernel: Rethinking Message Passing on Text-Rich Graphs
LLM-based graph kernel approach for text-rich graphs that preserves raw textual information in message passing instead of compressing to embeddings.
4/21/2026
In-Context Symbolic Regression for Robustness-Improved Kolmogorov-Arnold Networks
In-context symbolic regression framework for Kolmogorov-Arnold Networks to extract interpretable analytical expressions from learned functions.
4/21/2026
What If Consensus Lies? Selective-Complementary Reinforcement Learning at Test Time
Test-time RL method for LLMs using selective-complementary pseudo-rewards to improve reasoning when consensus voting is unreliable on dispersed answer distributions.
4/21/2026
Can we generate portable representations for clinical time series data using LLMs?
Study on using LLMs to generate portable patient embeddings from clinical time series for cross-hospital model deployment.
4/21/2026
Scaling Recurrence-aware Foundation Models for Clinical Records via Next-Visit Prediction
RAVEN: generative pretraining foundation model for electronic health records via recurrence-aware next-visit event prediction.
4/21/2026
Can LLMs Beat Classical Hyperparameter Optimization Algorithms? A Study on autoresearch
Comparison of LLM agents vs classical HPO algorithms (CMA-ES, TPE) for hyperparameter optimization on autoresearch testbed.
4/21/2026
ARCS: Autoregressive Circuit Synthesis with Topology-Aware Graph Attention and Spec Conditioning
ARCS: amortized analog circuit generation using graph VAE and flow-matching models, producing SPICE-simulatable designs in milliseconds.
4/21/2026
Toward Consistent World Models with Multi-Token Prediction and Latent Semantic Enhancement
Analysis of multi-token prediction in LLMs showing it promotes learning of structured world model representations.
4/21/2026
Weaves, Wires, and Morphisms: Formalizing and Implementing the Algebra of Deep Learning
Categorical mathematical framework for formalizing deep learning architectures, handling broadcasting and component composition.
4/21/2026
How to sketch a learning algorithm
Data deletion scheme for predicting model behavior after excluding training data subsets, relevant to interpretability and privacy.
4/21/2026
DMax: Aggressive Parallel Decoding for dLLMs
DMax: efficient diffusion language model decoding with aggressive parallelism via progressive self-refinement from masks to tokens.
4/21/2026
StructRL: Recovering Dynamic Programming Structure from Learning Dynamics in Distributional Reinforcement Learning
Method to recover dynamic programming structure from distributional reinforcement learning training dynamics.
4/21/2026
THEIA: Learning Complete Kleene Three-Valued Logic in a Pure-Neural Modular Architecture
THEIA: Modular neural architecture learning complete Kleene three-valued logic rules without symbolic inference, achieving 99% accuracy on all 39 K3 operators.
4/21/2026
Sample Complexity of Autoregressive Reasoning: Chain-of-Thought vs. End-to-End
PAC-learning theoretical analysis of sample complexity differences between chain-of-thought and end-to-end autoregressive generation in language models.
4/21/2026
GCA Framework: A GCC Countries-Grounded Dataset and Agentic Pipeline for Climate Decision Support
GCA framework combining curated climate dataset with agentic LLM pipeline for GCC country climate decision support and geospatial tool integration.
4/21/2026
Diffusion Sequence Models for Generative In-Context Meta-Learning of Robot Dynamics
Diffusion sequence models for meta-learning robot dynamics through in-context learning, comparing deterministic and generative approaches to system identification.