archive
Every paper Pith has read. Search by title, abstract, or pith.
14513 papers in cs.AI · page 11
-
Verifier rewards train neural translator to 86% LTL satisfiability
NeuroNL2LTL: A Neurosymbolic Framework for Natural Language Translation of Linear Temporal Logic
-
Reflector embeds reflection to block indirect jailbreaks
REFLECTOR: Internalizing Step-wise Reflection against Indirect Jailbreak
-
Early entropy drop signals when CoT reasoning helps LLMs
When Do LLMs Reason? A Dynamical Systems View via Entropy Phase Transitions
-
Attention model doubles perfect multi-user Wi-Fi activity predictions
AMAR: Lightweight Attention-Based Multi-User Activity Recognition from Wi-Fi CSI
-
Joint action-predicate model enables zero-shot robot skill composition
Jointly Learning Predicates and Actions Enables Zero-Shot Skill Composition
-
RL method produces ready-to-bend pipes for aeroengines
Design for Manufacturing: A Manufacturability Knowledge-Integrated Reinforcement Learning Framework for Free-Form Pipe Routing in Aeroengines
-
Self-distillation balances consensus across views to cut noise from privileged signals
AVSD: Adaptive-View Self-Distillation by Balancing Consensus and Teacher-Specific Privileged Signals
-
LLM compilation creates hidden backdoor attack surface
Trusted Weights, Treacherous Optimizations? Optimization-Triggered Backdoor Attacks on LLMs
-
Training supervision lifts portrait alignment
Pareto-Enhanced Portrait Generation: Vision-Aligned Text Supervision for Alignment, Realism, and Aesthetics
-
Temporal cache delivers 30.6x speedup on hits in agent pipelines
Evaluating Temporal Semantic Caching and Workflow Optimization in Agentic Plan-Execute Pipelines
-
Pipeline triples accuracy for Indigenous image captions
Retrieval-Augmented Long-Context Translation for Cultural Image Captioning: Gators submission for AmericasNLP 2026 shared task
-
Autoregressive diffusion cuts video restoration latency to seconds
Accelerating Video Inverse Problem Solvers with Autoregressive Diffusion Models
-
AI generates proofs for lower bounds on advection-diffusion mixing
Lower Bounds for Advection-Diffusion Equations: An Exploration with AI-Generated Proofs
-
Agents learn when to jump in vehicle routing search
COAgents: Multi-Agent Framework to Learn and Navigate Routing Problems Search Space
-
Animate-inanimate split structures vision MoE experts stably
Beyond Routing: Characterising Expert Tuning and Representation in Vision Mixture-of-Experts
-
Multi-agent system cuts 5G repair time by 86 percent
From Automated to Autonomous: Hierarchical Agent-native Network Architecture (HANA)
-
Self-training amplifies surface markers while deep syntax dies
Self-Training Doesn't Flatten Language -- It Restructures It: Surface Markers Amplify While Deep Syntax Dies
-
Failure notes lift diagnostic AI accuracy up to 7%
MedExpMem: Adapting Experience Memory for Differential Diagnosis
-
Unlearning by shifting erased points to retained semantic neighbors
Approximate Machine Unlearning through Manifold Representation Forgetting Guided by Self Mode Connectivity
-
JAX simulator runs Mahjong at 2 million steps per second
Mahjax: A GPU-Accelerated Mahjong Simulator for Reinforcement Learning in JAX
-
Small models copy last CoT number for 89-92% of arithmetic accuracy
The Readout Shortcut: Positional Number Copying Dominates Arithmetic CoT Readout in Small Language Models
-
State management beats workspace isolation in multi-agent tasks
Multi-agent Collaboration with State Management
-
Logit averaging in GRPO matches KL-regularized accuracy
Complementing reinforcement learning with SFT through logit averaging in the post training of LLMs
-
AI agents enable precise tests of negotiator personality
Personality Engineering with AI Agents: A New Methodology for Negotiation Research
-
Weighted clusters plus pruning give flexible speed-accuracy control in VPR
Faster or Stronger: Towards Flexible Visual Place Recognition via Weighted Aggregation and Token Pruning
-
Learn image-space generators matching latent-process marginals
Latent Process Generator Matching
-
Geometric axioms explain neural network mechanisms
Axiomatizing Neural Networks via Pursuit of Subspaces
-
LLM agent accuracy drops to 0.54-0.62 without labels
AgentAtlas: Beyond Outcome Leaderboards for LLM Agents
-
Co-occurrence patterns support subject-verb agreement learning
Collocational bootstrapping: A hypothesis about the learning of subject-verb agreement in humans and neural networks
-
AI models lag behind text-only on 3D brain MRI benchmark
NeuroQA: A Large-Scale Image-Grounded Benchmark for 3D Brain MRI Understanding
5 Piths -
Compact neural net edges FIB-4 on advanced MASLD fibrosis detection
Machine-Learning-Enhanced Non-Invasive Testing for MASLD Fibrosis: Shallow-Deep Neural Networks Versus FIB-4, Tabular Foundation Models, and Large Language Models
-
AI agent ships iOS app with one fix
Open-World Evaluations for Measuring Frontier AI Capabilities
-
Latent-space attacks survive audio codec compression
Codec-Robust Attacks on Audio LLMs
-
Latent-space attacks survive codec compression on audio LLMs
Codec-Robust Attacks on Audio LLMs
-
Dataset pairs building models with shade maps for urban heat studies
ShadeBench: A Benchmark Dataset for Building Shade Simulation in Sustainable Society
-
Min-gate fuses diffusion models to catch all four OOD shifts
Tippett-minimum Fusion of Representation-space Diffusion Models for Multi-Encoder Out-of-Distribution Detection
-
New metrics score uncertainty-augmented systems as one proper rule
ECUAS$_n$: A family of metrics for principled evaluation of uncertainty-augmented systems
-
ECUAS_n metrics score uncertainty-augmented systems with one tunable rule
ECUAS$_n$: A family of metrics for principled evaluation of uncertainty-augmented systems
-
Trained reflectors improve language agents on new tasks
Training Language Agents to Learn from Experience
-
Code gen picks winner by clustering behaviors on auto-generated inputs
Code Generation by Differential Test Time Scaling
-
Projection equivariance lifts CBCT-to-CT PSNR by 7 dB
EPC-3D-Diff: Equivariant Physics Consistent Conditional 3D Latent Diffusion for CBCT to CT Synthesis
-
Triplet loss creates high-quality embeddings for Horn logic
High Quality Embeddings for Horn Logic Reasoning
-
Deep learning segments COVID lesions in CT with high accuracy
Pixel Wised Lesion Prediction on COVID-19 CT Imagery: A Comparative Analysis of Automated Image Segmentation Architectures
-
Agentic AI coding improves with structured verification loops
Agentic Agile-V: From Vibe Coding to Verified Engineering in Software and Hardware Development
-
Linear probes on frozen LLMs forecast time series without supervision
LLM Pretraining Shapes a Generalizable Manifold: Insights into Cross-Modal Transfer to Time Series
-
ResNet and VGG hit 95-98 percent accuracy on COVID lung scans
A Comprehensive Comparison of Deep Learning Architectures for COVID-19 Classification on CT & X-ray Imagery
-
AI agents form distinct emotional signatures on Moltbook
Modeling Emotional Dynamics in Agent-to-Agent Interactions on Moltbook
-
Weight decay separates memorization
Weight Decay Regimes in Grokking Transformers: Cheap Online Diagnostics
-
Tensor algebra recovers angular-momentum rules from molecules alone
Group-Algebraic Tensors: Provably-optimal Equivariant Learning and Physical Symmetry Discovery
-
Routing weights produce hierarchical attributions at zero cost
BOHM: Zero-Cost Hierarchical Attribution for Compound AI Systems