3/10/2026
Learning Quadruped Walking from Seconds of Demonstration
Imitation learning approach for quadruped locomotion exploiting limit cycle structure to achieve effective learning from minimal demonstration data.
3/10/2026
Elenchus: Generating Knowledge Bases from Prover-Skeptic Dialogues
Elenchus system for knowledge base construction through prover-skeptic dialogue between LLM and human expert, grounded in inferentialist semantics.
3/10/2026
A Systematic Investigation of Document Chunking Strategies and Embedding Sensitivity
Large-scale benchmark of 36 document chunking strategies across domains for retrieval-augmented systems, evaluating segment methods with multiple embedding models.
3/10/2026
NePPO: Near-Potential Policy Optimization for General-Sum Multi-Agent Reinforcement Learning
Multi-agent reinforcement learning algorithm addressing training stability and convergence in general-sum games with heterogeneous agent preferences.
3/10/2026
Diffusion Controller: Framework, Algorithms and Parameterization
Unified control-theoretic framework casting diffusion model generation as stochastic control within linearly-solvable MDPs.
3/10/2026
Foundational World Models Accurately Detect Bimanual Manipulator Failures
Foundational world models for detecting bimanual manipulator failures using probabilistic methods on high-dimensional visual and proprioceptive data.
3/10/2026
Can Safety Emerge from Weak Supervision? A Systematic Analysis of Small Language Models
Self-MOA method for achieving safety alignment in small language models using weak supervision instead of large human-annotated datasets.
3/10/2026
RESCHED: Rethinking Flexible Job Shop Scheduling from a Transformer-based Architecture with Simplified States
Transformer-based approach to flexible job shop scheduling that reduces reliance on handcrafted features and uses simplified state representations.
3/10/2026
Hit-RAG: Learning to Reason with Long Contexts via Preference Alignment
Hit-RAG method addresses attention dilution in retrieval-augmented generation for multimodal LLMs using preference alignment to reason over long contexts.
3/10/2026
Looking Back and Forth: Cross-Image Attention Calibration and Attentive Preference Learning for Multi-Image Hallucination Mitigation
Framework for mitigating hallucinations in vision-language models on multi-image tasks through cross-image attention calibration and preference learning.
3/10/2026
User Review Writing via Interview with Dialogue Systems
Proposes dialogue system approach for generating user reviews from interview conversations using GPT-4 to reduce time and effort in review creation.
3/10/2026
Countdown-Code: A Testbed for Studying The Emergence and Generalization of Reward Hacking in RLVR
Introduces Countdown-Code testbed environment enabling clean measurement of reward hacking in reinforcement learning via access to both task reward and test harness manipulation.
3/10/2026
Efficient Personalized Reranking with Semi-Autoregressive Generation and Online Knowledge Distillation
Presents semi-autoregressive generative model for personalized reranking in recommender systems balancing generation quality with low-latency inference via knowledge distillation.
3/10/2026
Enhancing Consistency of Werewolf AI through Dialogue Summarization and Persona Information
Develops LLM-based Werewolf game agent using dialogue summarization and persona information to improve consistency and reasoning in multi-player communication games.
3/10/2026
aCAPTCHA: Verifying That an Entity Is a Capable Agent via Asymmetric Hardness
Proposes aCAPTCHA verification system to detect autonomous AI agents using asymmetric hardness based on action, reasoning, and memory capabilities as security measure.
3/10/2026
Deep Expert Injection for Anchoring Retinal VLMs with Domain-Specific Knowledge
Addresses gaps in vision-language models for ophthalmic diagnosis by injecting domain-specific knowledge to resolve fine-grained pathological cues and improve clinical reasoning.
3/10/2026
Emotion Transcription in Conversation: A Benchmark for Capturing Subtle and Complex Emotional States through Natural Language
Introduces Emotion Transcription in Conversation task generating natural language descriptions of complex emotional states rather than categorical labels for human-machine interaction.
3/10/2026
Fine-Grained Table Retrieval Through the Lens of Complex Queries
Presents fine-grained table retrieval mechanism using typed query decomposition and connectivity-awareness for natural language question answering over tabular data.
3/10/2026
Governance Architecture for Autonomous Agent Systems: Threats, Framework, and Engineering Practice
Proposes Layered Governance Architecture for securing autonomous LLM agents against prompt injection, retrieval poisoning, and tool misuse through execution sandboxing, intent verification, and zero-trust authorization.
3/10/2026
A Miniature Brain Transformer: Thalamic Gating, Hippocampal Lateralization, Amygdaloid Salience, and Prefrontal Working Memory in Attention-Coupled Latent Memory
Miniature brain transformer architecture incorporating thalamic, hippocampal, amygdaloid, and prefrontal components for attention-coupled latent memory.
3/10/2026
VINO: Video-driven Invariance for Non-contextual Objects via Structural Prior Guided De-contextualization
VINO: Self-supervised learning method using video to learn invariant representations of foreground objects while resisting contextual shortcuts.
3/10/2026
LEPA: Learning Geometric Equivariance in Satellite Remote Sensing Data with a Predictive Architecture
LEPA: Learning geometric equivariance in satellite remote sensing data to handle mismatches between precomputed embeddings and user-defined areas of interest.
3/10/2026
Learning When to Cooperate Under Heterogeneous Goals
Research on multi-agent learning for determining when to cooperate versus work independently under heterogeneous goals in open-ended environments.
3/10/2026
Kinematics-Aware Latent World Models for Data-Efficient Autonomous Driving
Kinematics-aware latent world models for data-efficient autonomous driving using recurrent state-space models with explicit spatial-kinematic encoding.
3/10/2026
Do Deployment Constraints Make LLMs Hallucinate Citations? An Empirical Study across Four Models and Five Prompting Regimes
Empirical study examining how deployment constraints and prompting strategies affect LLM citation hallucination across four models in academic and SE contexts.
3/10/2026
MAviS: A Multimodal Conversational Assistant For Avian Species
MAviS: Multimodal conversational assistant for avian species with specialized dataset for fine-grained biodiversity and species-specific question answering.
3/10/2026
Adversarial Latent-State Training for Robust Policies in Partially Observable Domains
Adversarial latent-state training for robust reinforcement learning policies under hidden distribution shift in partially observable environments.
3/10/2026
Norm-Hierarchy Transitions in Representation Learning: When and Why Neural Networks Abandon Shortcuts
Research on norm-hierarchy transitions explaining when and why neural networks transition from spurious shortcuts to structured representations during training.
3/10/2026
Agora: Teaching the Skill of Consensus-Finding with AI Personas Grounded in Human Voice
Agora: AI-powered platform using LLM personas to teach consensus-finding and deliberative skills at scale for civic competence development.
3/10/2026
Learning Concept Bottleneck Models from Mechanistic Explanations
Learning Concept Bottleneck Models from mechanistic explanations using LLMs to discover predictive concepts without human specification.
3/10/2026
AgrI Challenge: A Data-Centric AI Competition for Cross-Team Validation in Agricultural Vision
AgrI Challenge: data-centric ML competition evaluating model generalization in agricultural vision under real-world distribution shift conditions.
3/10/2026
Latent Generative Models with Tunable Complexity for Compressed Sensing and other Inverse Problems
Tunable-complexity priors for diffusion models and normalizing flows to address limitations of fixed-complexity generative models in inverse problems.
3/10/2026
Scaling Laws in the Tiny Regime: How Small Models Change Their Mistakes
Scaling laws study examining how sub-20M parameter models (TinyML/edge AI) follow power-law performance curves across architectures on CIFAR-100.
3/10/2026
Position: LLMs Must Use Functor-Based and RAG-Driven Bias Mitigation for Fairness
Position paper proposing functor-based and RAG-driven approaches to mitigate demographic and gender biases in large language models.
3/10/2026
Domain-Specific Quality Estimation for Machine Translation in Low-Resource Scenarios
Study on quality estimation for machine translation in low-resource scenarios using zero-shot and few-shot prompting techniques across multiple language pairs and domains.
3/10/2026
Scheduling Parallel Optical Circuit Switches for AI Training
Research on scheduling parallel optical circuit switches for AI training datacenter infrastructure, focusing on energy efficiency and bandwidth optimization.
3/10/2026
AQuA: Toward Strategic Response Generation for Ambiguous Visual Questions
arXiv paper: AQuA benchmark for visual question answering addressing ambiguous images requiring nuanced reasoning strategies.
3/10/2026
Adaptive Capacity Allocation for Vision Language Action Fine-tuning
arXiv paper: Parameter-efficient fine-tuning for vision-language-action models with adaptive capacity allocation for robotics transfer.
3/10/2026
UnSCAR: Universal, Scalable, Controllable, and Adaptable Image Restoration
arXiv paper: UnSCAR universal image restoration using scalable architecture for multiple degradation types.
3/10/2026
Machine Learning for the Internet of Underwater Things: From Fundamentals to Implementation
arXiv paper: ML techniques for underwater IoT systems addressing acoustic constraints and energy limitations. Niche domain application.
3/10/2026
Dial: A Knowledge-Grounded Dialect-Specific NL2SQL System
NL2SQL system supporting heterogeneous SQL dialects with knowledge grounding for semantic correctness and database executability.
3/10/2026
Backdoor4Good: Benchmarking Beneficial Uses of Backdoors in LLMs
Benchmark framework for beneficial backdoor applications in LLMs as controllable auditable interfaces for trustworthy behavior.
3/10/2026
Image Generation Models: A Technical History
Comprehensive technical survey of image generation models including VAEs, GANs, flows, autoregressive, transformers, and diffusion methods.
3/10/2026
Where Do LLM-based Systems Break? A System-Level Security Framework for Risk Assessment and Treatment
System-level security framework for LLM-powered applications using Attack-Defense Trees and CVSS scoring for risk assessment.
3/10/2026
The Dual-Stream Transformer: Channelized Architecture for Interpretable Language Modeling
Dual-Stream Transformer architecture decomposing computation into token and context streams for interpretable language modeling.
3/10/2026
Give Them an Inch and They Will Take a Mile:Understanding and Measuring Caller Identity Confusion in MCP-Based AI Systems
Security analysis of Model Context Protocol (MCP) integration in LLM-based AI agents, identifying caller identity confusion vulnerabilities.
3/10/2026
Cross-Modal Taxonomic Generalization in (Vision-) Language Models
Study of semantic alignment between language models and vision-language models for cross-modal taxonomic generalization.
3/10/2026
From Thinker to Society: Security in Hierarchical Autonomy Evolution of AI Agents
Security framework for LLM-based AI agents, analyzing vulnerabilities in hierarchical autonomy evolution.
3/10/2026
SeDa: A Unified System for Dataset Discovery and Multi-Entity Augmented Semantic Exploration
SeDa system for discovering and exploring 7.6M datasets across 200+ open platforms with semantic annotation.
3/10/2026
Learning-free L2-Accented Speech Generation using Phonological Rules
Accented TTS framework combining phonological rules with multilingual model for phoneme-level accent control without large datasets.