AI News

⚡ 11 minutes ago
1
1
OPD+: Rethinking the Advantage Design for On-Policy Distillation (arxiv.org)
2
1
Plausibility Is Not Prediction: Contrastive Evidence for LLM-Based Cellular Perturbation Reasoning (arxiv.org)
3
1
Interaction-Limited Safe Continuous-Time RL for Dynamical Medical Treatment (arxiv.org)
4
1
Repair Before Veto: Repair-Augmented Constraint Learning for Contextual Decisions (arxiv.org)
5
1
Coordination Graphs for Constrained Multi-Agent Reinforcement Learning (arxiv.org)
6
1
SIRI: Self-Internalizing Reinforcement Learning with Intrinsic Skills for LLM Agent Training (arxiv.org)
7
1
MOC: Multi-Order Communication in LLM-based Multi-Agent Systems (arxiv.org)
8
1
Improving Hospital Process Management through Process Mining: A Case Study on COVID-19 Clinical Pathways (arxiv.org)
9
1
Non-Vacuous Certification of Transport MCMC via Oscillation-Controlled Normalizing Flows (arxiv.org)
10
1
ThinkSwitch: Context Distillation with LoRA and Weight Interpolation for Specific-Purpose Reasoning Tasks (arxiv.org)
11
1
Decision-Focused On-Policy Learning for Contextual Linear Optimization with Partial Feedback (arxiv.org)
12
1
MViewRouter: Internalizing Geometric Equivariance via Multi-view Alternating Attention for Combinatorial Routing (arxiv.org)
13
1
PaCX-MAE: Physiology-Augmented Chest X-Ray Masked Autoencoder (arxiv.org)
14
1
COMAP: Co-Evolving World Models and Agent Policies for LLM Agents (arxiv.org)
15
1
Harness-1: Reinforcement Learning for Search Agents with State-Externalizing Harnesses (arxiv.org)
16
1
Spatial Representation Learning Beyond Pixels: Unifying Raster Data and Vector Semantics for Human-Centric Geospatial Foundation Models (arxiv.org)
17
1
A Mathematical Conflict Framework for Contextual Data Modulation (arxiv.org)
18
1
AgentPLM: Agentic Protein Language Models with Reasoning-Augmented Decoding for Protein Sequence Design (arxiv.org)
19
1
A Fiber Criterion for Representation Identifiability in Supervised Learning (arxiv.org)
20
1
Soft-NBCE: Entropy-Weighted Chunk Fusion for Long-Context (arxiv.org)
21
1
LeAP: Learnable Adaptive Permutation for Feature Selection in Heterogeneous and Sparse Recommender Systems (arxiv.org)
22
1
HASTE: Hardware-Aware Dynamic Sparse Training for Large Output Spaces (arxiv.org)
23
1
A Per-Component Diagnostic Protocol for Neural HJB-PIDE Solvers under Control-Dependent L\'evy Jumps (arxiv.org)
24
1
From Reward-Free Representations to Preferences: Rethinking Offline Preference-Based Reinforcement Learning (arxiv.org)
25
1
Bridging the Sim-to-Real Gap in Semiconductor Visual Program Synthesis via Input Binarization (arxiv.org)
26
1
HLL: Can Agents Cross Humanity's Last Line of Verification? (arxiv.org)
27
1
Beyond One-shot: AI Agents for Learning in Field Experiments (arxiv.org)
28
1
AGENTCL: Toward Rigorous Evaluation of Continual Learning in Language Agents (arxiv.org)
29
1
MCP-Persona: Benchmarking LLM Agents on Real-World Personal Applications via Environment Simulation (arxiv.org)
30
1
Accuracy, Stability, and Repeated-Run Reliability of Large Language Models on Deterministic Programming Tasks (arxiv.org)
31
1
Conditioned free-energy density of proteins using unbalanced solutions to constraint satisfaction problems (arxiv.org)
32
1
CSRP: Chain-of-Thought Reasoning for Chinese Text Correction via Reinforcement Learning with Efficiency-Aware Rewards (arxiv.org)
33
1
FreqLite: A Lightweight Frequency-Decomposed Linear Model with Adaptive Reversible Normalization for Robust Long-Term Time-Series Forecasting (arxiv.org)
34
1
SENSE: Semantic Embedding Navigation with Soft-gated Evaluation for Retrieval-based Speculative Decoding (arxiv.org)
35
1
All Models are Wrong, Knowing Where is Useful: On Model Uncertainty in Reinforcement Learning (arxiv.org)
36
1
lmfaoooo at SemEval-2026 Task 1: Humor Is an Audience. Preference Modeling for Constrained Humor Generation (arxiv.org)
37
1
TrustLDM: Benchmarking Trustworthiness in Language Diffusion Models (arxiv.org)
38
1
A Multi-Domain Red Teaming Framework for Safety, Robustness, and Fairness Evaluation of Medical Large Language Models (arxiv.org)
39
1
TCAR-Gen: Temporal Graph Retrieval with Evidence Fusion for Knowledge-Grounded Generation (arxiv.org)
40
1
Measuring and Mitigating Bias in Code Generated by Large Language Models (arxiv.org)
41
1
From Performance to Viability: A Bootstrap Framework for Latent-Space Representation Learning in Adaptive Biological Systems (arxiv.org)
42
1
Turning Back Without Forgetting: Selective Backward Refinement for Parameter-Efficient Continual Learning (arxiv.org)
43
1
Efficient Exploration for Iterative Nash Preference Optimization (arxiv.org)
44
1
Neural Network Compression by Approximate Differential Equivalence (arxiv.org)
45
1
ProbMoE: Differentiable Probabilistic Routing for Mixture-of-Experts (arxiv.org)
46
1
Business Utility of Large Language Models as Exploratory Data Analysis Agents (arxiv.org)
47
1
LLMs for Cardiovascular Risk Prediction from Structured Clinical Data (arxiv.org)
48
1
Make Mechanistic Interpretability Auditable: A Call to Develop Guidelines via Continuous Collaborative Reviewing (arxiv.org)
49
1
Update Opacity: Epistemic Accessibility and Governance Under AI System Change (arxiv.org)
50
1
Beyond Tool Adoption: A Practical Five-Stage Developmental Continuum for AI Literacy in Higher Education (arxiv.org)