3/30/2026
Defending Against Knowledge Poisoning Attacks During Retrieval-Augmented Generation
Defends RAG systems against knowledge poisoning attacks by detecting and mitigating adversarial text injections in external knowledge sources.
3/30/2026
PepThink-R1: LLM for Interpretable Cyclic Peptide Optimization with CoT SFT and Reinforcement Learning
PepThink-R1 integrates LLMs with chain-of-thought supervised fine-tuning and reinforcement learning for interpretable cyclic peptide design optimization.
3/30/2026
Large Language Models Can Perform Automatic Modulation Classification via Discretized Self-supervised Candidate Retrieval
LLMs perform automatic wireless modulation classification via discretized self-supervised candidate retrieval, avoiding distribution shift issues of supervised models.
3/30/2026
Activation Steering with a Feedback Controller
Control-theoretic framework for LLM activation steering with feedback controllers, connecting empirical steering methods to proportional control theory for safety alignment.
3/30/2026
NeST-BO: Fast Local Bayesian Optimization via Newton-Step Targeting of Gradient and Hessian Information
NeST-BO proposes Newton-step targeting Bayesian optimization using Gaussian processes to learn gradient and Hessian information for expensive black-box problems.
3/30/2026
Route Experts by Sequence, not by Token
Sequence-level TopK (SeqTopK) improves Mixture-of-Experts routing in LLMs by adapting expert assignment per sequence rather than per token without retraining.
3/30/2026
Cascading Bandits With Feedback
Cascading Bandits analyzes decision-making policies for edge inference with multiple models, providing theoretical regret guarantees for Explore-then-Commit and Thompson Sampling approaches.
3/30/2026
LiteCache: A Query Similarity-Driven, GPU-Centric KVCache Subsystem for Efficient LLM Inference
LiteCache optimizes KVCache memory management for LLM inference using GPU-centric query similarity-driven approach to reduce memory overhead and improve CUDA Graph execution.
3/30/2026
ReBaPL: Repulsive Bayesian Prompt Learning
Repulsive Bayesian Prompt Learning addresses overfitting in prompt learning for foundation models using Bayesian inference framework for improved out-of-distribution generalization.
3/30/2026
Aligning LLMs with Biomedical Knowledge using Balanced Fine-Tuning
Balanced Fine-Tuning aligns LLMs with biomedical knowledge through confidence-weighted token-level optimization and adaptive reward mechanisms.
3/30/2026
FedRE: A Representation Entanglement Framework for Model-Heterogeneous Federated Learning
FedRE proposes a representation entanglement framework enabling federated learning across clients with heterogeneous model architectures and data.
3/30/2026
SonicMoE: Accelerating MoE with IO and Tile-aware Optimizations
SonicMoE optimizes Mixture of Experts inference through IO-aware and tile-aware techniques for high-granularity, sparse MoE language models.
3/30/2026
Concurrent training methods for Kolmogorov-Arnold networks: Disjoint datasets and FPGA implementation
Concurrent training enhancements for Kolmogorov-Arnold networks using Newton-Kaczmarz method with FPGA implementation for improved efficiency.
3/30/2026
The Dual-State Architecture for Reliable LLM Agents
Dual-State Action Pair (DSAP) primitive couples stochastic LLM generation with deterministic verification for reliable code generation agents.
3/30/2026
Extending Puzzle for Mixture-of-Experts Reasoning Models with Application to GPT-OSS Acceleration
Extends Puzzle neural architecture search to reasoning LLMs, producing gpt-oss-puzzle-88B through MoE expert pruning and inference optimization.
3/30/2026
Quantization-Robust LLM Unlearning via Low-Rank Adaptation
Combines low-rank adaptation with quantization-aware unlearning to ensure LLM knowledge removal survives post-training 4-bit quantization.
3/30/2026
Golden Layers and Where to Find Them: Improved Knowledge Editing for Large Language Models Via Layer Gradient Analysis
Golden Layers method improves LLM knowledge editing via layer gradient analysis to identify optimal depth for updating model predictions per query.
3/30/2026
cc-Shapley: Measuring Multivariate Feature Importance Needs Causal Context
cc-Shapley extends Shapley values for multivariate feature importance by incorporating causal context to address spurious associations.
3/30/2026
Efficient Continual Learning in Language Models via Thalamically Routed Cortical Columns
TRC² architecture for continual learning in LLMs preventing catastrophic forgetting through decoder-only thalamic routing of cortical columns.
3/30/2026
AgentTrace: Causal Graph Tracing for Root Cause Analysis in Deployed Multi-Agent Systems
AgentTrace framework for post-hoc root cause analysis in deployed multi-agent systems via causal graph reconstruction from execution logs.
3/30/2026
Neural Uncertainty Principle: A Unified View of Adversarial Fragility and LLM Hallucination
Connects adversarial robustness and LLM hallucinations through shared geometric principle formalized as Neural Uncertainty Principle with irreducible uncertainty bounds.
3/30/2026
mSFT: Addressing Dataset Mixtures Overfitting Heterogeneously in Multi-task SFT
mSFT algorithm addresses overfitting in multi-task supervised fine-tuning by dynamically adjusting data mixture ratios based on task-specific learning dynamics.
3/30/2026
Decoupling Exploration and Policy Optimization: Uncertainty Guided Tree Search for Hard Exploration
Decouples exploration from policy optimization in RL using uncertainty-guided tree search for efficient autonomous exploration without intrinsic motivation.
3/30/2026
Steering Code LLMs with Activation Directions for Language and Library Control
Method for steering code LLMs toward specific programming languages and libraries by manipulating activation space directions at inference time, tested on five language/library pairs across three open-weight models.
3/30/2026
The Alignment Tax: Response Homogenization in Aligned LLMs and Its Implications for Uncertainty Estimation
Analysis of response homogenization in RLHF-aligned LLMs showing reduced uncertainty estimation and implications for sampling.
3/30/2026
Missing-Aware Multimodal Fusion for Unified Microservice Incident Management
Multimodal fusion approach for microservice incident detection handling missing modalities without static imputation.
3/30/2026
CACTO-SL: Using Sobolev Learning to improve Continuous Actor-Critic with Trajectory Optimization
Actor-critic reinforcement learning approach combining trajectory optimization with Sobolev learning for optimal control.
3/30/2026
Towards Knowledge Guided Pretraining Approaches for Multimodal Foundation Models: Applications in Remote Sensing
Knowledge-guided pretraining framework for multimodal foundation models applied to remote sensing applications.
3/30/2026
Reproducibility and Artifact Consistency of the SIGIR 2022 Recommender Systems Papers Based on Message Passing
Reproducibility analysis of 10 graph-based neural recommender papers from SIGIR 2022 assessing methodology and impact.
3/30/2026
Diffusion Recommender Models and the Illusion of Progress: A Concerning Study of Reproducibility and a Conceptual Mismatch
Reproducibility study of diffusion-based recommender systems identifying methodological issues and limited actual progress.
3/30/2026
Is Supervised Learning Really That Different from Unsupervised?
Theoretical analysis showing supervised learning can be decomposed into unsupervised parameter selection plus label addition.
3/30/2026
StreamDiT: Real-Time Streaming Text-to-Video Generation
Real-time streaming text-to-video generation model using transformer-based diffusion for interactive applications.
3/30/2026
Out-of-Sight Embodied Agents: Multimodal Tracking, Sensor Fusion, and Trajectory Forecasting
Multimodal approach for trajectory prediction with sensor fusion and tracking for embodied agents in occluded scenarios.
3/30/2026
ORIC: Benchmarking Object Recognition under Contextual Incongruity in Large Vision-Language Models
Benchmark (ORIC) examining vision-language model failures in object recognition under contextual incongruity scenarios.
3/30/2026
Beyond Log Likelihood: Probability-Based Objectives for Supervised Fine-Tuning across the Model Capability Continuum
Study on alternative training objectives for LLM fine-tuning beyond negative log likelihood to improve generalization.
3/30/2026
Bayesian Optimization on Networks
Bayesian optimization algorithms on metric graphs using Gaussian process surrogates for expensive black-box function evaluation.
3/30/2026
GUI-AIMA: Aligning Intrinsic Multimodal Attention with a Context Anchor for GUI Grounding
GUI-AIMA alignment method for MLLMs to ground natural language instructions to UI regions, enabling computer-use agents via visual grounding.
3/30/2026
PriVi: Towards A General-Purpose Video Model For Primate Behavior In The Wild
PriVi foundation model for primate behavior analysis in video, data-centric computer vision approach for non-human animal research.
3/30/2026
Architecting software monitors for control-flow anomaly detection through large language models and conformance checking
Framework combining LLMs and conformance checking for detecting control-flow anomalies in software monitoring, security application.
3/30/2026
WorldMM: Dynamic Multimodal Memory Agent for Long Video Reasoning
WorldMM memory-augmented video LLM agent for reasoning over hours-long videos with multimodal memory, addressing long-context understanding.
3/30/2026
Hear What Matters! Text-conditioned Selective Video-to-Audio Generation
SELVA model for text-conditioned selective video-to-audio generation, enabling fine-grained audio control from multimodal video input.
3/30/2026
Nemotron-Cascade: Scaling Cascaded Reinforcement Learning for General-Purpose Reasoning Models
Nemotron-Cascade framework scaling reinforcement learning for general-purpose reasoning models, addressing heterogeneity in response lengths and verification latency.
3/30/2026
Uncovering Patterns of Brain Activity from EEG Data Consistently Associated with Cybersickness Using Neural Network Interpretability Maps
Neural network interpretability approach for identifying EEG patterns associated with cybersickness in VR, application of ML for neuroscience.
3/30/2026
NRR-Phi: Text-to-State Mapping for Ambiguity Preservation in LLM Inference
Framework preserving ambiguity in LLM inference through non-collapsing state spaces, addressing premature semantic commitment in dialogue systems.
3/30/2026
From Pixels to Patches: Pooling Strategies for Earth Embeddings
Analysis of pooling strategies for aggregating pixel-level embeddings from geospatial foundation models to patch-level representations.
3/30/2026
Entropy trajectory shape predicts LLM reasoning reliability: A diagnostic study of uncertainty dynamics in chain-of-thought
Diagnostic approach using entropy trajectory shapes to predict reasoning reliability in chain-of-thought LLM outputs, practical for uncertainty quantification.
3/30/2026
KALAVAI: Predicting When Independent Specialist Fusion Works -- A Quantitative Model for Post-Hoc Cooperative LLM Training
KALAVAI protocol predicting when independently trained specialist LLMs can be fused post-hoc, with quantitative formula for cooperative value estimation.
3/30/2026
MDKeyChunker: Single-Call LLM Enrichment with Rolling Keys and Key-Based Restructuring for High-Accuracy RAG
MDKeyChunker pipeline for structure-aware document chunking and single-call LLM enrichment to improve RAG accuracy, addressing semantic fragmentation in retrieval.
3/30/2026
UniScale: Synergistic Entire Space Data and Model Scaling for Search Ranking
Scaling law research for search ranking systems examining synergy between data and model architecture, inspired by LLM advances with industrial applications.
3/30/2026
Shape and Substance: Dual-Layer Side-Channel Attacks on Local Vision-Language Models
Side-channel attack framework exploiting dynamic high-resolution preprocessing in on-device vision-language models, revealing privacy risks from architectural design choices.