6/2/2026
FlowPlace: Flow Matching for Chip Placement
FlowPlace: flow matching generative model for chip placement overcoming synthetic data pre-training and sampling time limitations.
6/2/2026
How Can Reinforcement Learning Achieve Expert-level Placement?
Reinforcement learning approach for chip placement learning from expert layouts to achieve expert-quality physical design.
6/2/2026
MedSynapse-V: Bridging Visual Perception and Clinical Intuition via Latent Memory Evolution
MedSynapse-V framework addressing cognitive misalignment in medical vision-language models through latent memory evolution.
6/2/2026
Defeasible Conditional Obligation in a Two-tiered Preference-based Semantics (Extended Version)
Two-tiered preference-based semantics framework for modeling defeasible conditional obligations in deontic logic.
6/2/2026
Beyond Visual Fidelity: Benchmarking Super-Resolution Models for Large-Scale Remote Sensing Imagery via Downstream Task Integration
Benchmark for super-resolution models in satellite imagery evaluated on downstream Earth observation tasks.
6/2/2026
Possibilistic Predictive Uncertainty for Deep Learning
Method for epistemic uncertainty modeling in deep neural networks balancing Bayesian principled estimates with computational efficiency.
6/2/2026
STABLEVAL: Disagreement-Aware and Stable Evaluation of AI Systems
STABLEVAL framework for disagreement-aware evaluation of AI systems, modeling latent item correctness and annotator reliability to improve ranking stability.
6/2/2026
Gradients with Respect to Semantics Preserving Embeddings Tell the Uncertainty of Large Language Models
SemGrad: gradient-based uncertainty quantification method for LLM free-form generation, sampling-free and computationally efficient alternative to existing approaches.
6/2/2026
MidSteer: Optimal Affine Framework for Steering Generative Models
Theoretical framework for steering intermediate representations in generative models, formalizing concept steering through affine concept erasure.
6/2/2026
Do Joint Audio-Video Generation Models Understand Physics?
AV-Phys Bench: benchmark evaluating physical commonsense understanding in joint audio-video generation models.
6/2/2026
Why Self-Inconsistency Arises in GNN Explanations and How to Exploit It
Analysis of self-inconsistency in graph neural network explanations caused by re-explanation-induced context perturbation.
6/2/2026
Prune-OPD: Efficient and Reliable On-Policy Distillation for Long-Horizon Reasoning
Prune-OPD: efficient on-policy distillation for long-horizon LLM reasoning by pruning diverged trajectories.
6/2/2026
Normalization Equivariance for Arbitrary Backbones, with Application to Image Denoising
Normalization equivariance structural prior for improving robustness to distribution shift in image-to-image tasks like denoising.
6/2/2026
The Cartesian Shortcut: Re-evaluate Vision Reasoning in Polar Coordinate Space
Analysis of Cartesian Shortcut vulnerability in vision-reasoning benchmarks where orthogonal grid layouts enable coordinate exploitation.
6/2/2026
OGLS-SD: On-Policy Self-Distillation with Outcome-Guided Logit Steering for LLM Reasoning
Self-distillation method with outcome-guided logit steering to improve LLM reasoning through on-policy learning.
6/2/2026
Multi-Rollout On-Policy Distillation via Peer Successes and Failures
On-policy distillation approach leveraging peer trajectories to provide denser token-level supervision for LLM reasoning improvement.
6/2/2026
REALISTA: Realistic Latent Adversarial Attacks that Elicit LLM Hallucinations
Adversarial attack method for eliciting LLM hallucinations through semantically coherent prompts with constrained optimization.
6/2/2026
RISED: A Pre-Deployment Evaluation Framework for High-Stakes AI Decision-Support Systems, with Application to Healthcare
RISED: pre-deployment evaluation framework for clinical decision-support AI systems across reliability, inclusivity, and operational dimensions.
6/2/2026
Revisiting Reinforcement Learning with Verifiable Rewards from a Contrastive Perspective
Contrastive reformulation of GRPO for LLM post-training on reasoning tasks revealing limitations in reward design.
6/2/2026
CLIP Tricks You: Training-free Token Pruning for Efficient Pixel Grounding in Large VIsion-Language Models
Training-free token pruning method for reducing visual token overhead in vision-language models while preserving pixel grounding.
6/2/2026
Towards a holistic understanding of Selection Bias for Causal Effect Identification
Causal inference framework for identifying treatment effects in presence of selection bias from observational data.
6/2/2026
Many-Shot CoT-ICL: Making In-Context Learning Truly Learn
Analysis of many-shot chain-of-thought in-context learning for reasoning tasks across various LLM architectures and task types.
6/2/2026
AttenA+: Rectifying Action Inequality in Robotic Foundation Models
Robotic foundation model improvements by rectifying action inequality through attention-based weighting of trajectory segments.
6/2/2026
Topology-Preserving Neural Operator Learning via Hodge Decomposition
Neural operator learning framework using Hodge decomposition to preserve topology in solution operators on geometric meshes.
6/2/2026
Beyond AI as Assistants: Toward Autonomous Discovery in Cosmology
Autonomous AI agents for scientific discovery in cosmology using LLM-guided code evolution and multi-agent research laboratories.
6/2/2026
PBT-Bench: Benchmarking AI Agents on Property-Based Testing
PBT-Bench: benchmark for evaluating AI agents on property-based testing, measuring semantic invariant derivation and input-generation strategy construction.
6/2/2026
Avoiding Structural Failure Modes in Tabular Fair SSL: Online Primal-Dual Allocation under Confidence Gating
Semi-supervised learning approach for fairness in tabular data with analysis of failure modes in confidence-gated pseudo-labeling.
6/2/2026
Physics-Guided Geometric Diffusion for Macro Placement Generation
Physics-guided diffusion framework for VLSI chip macro placement optimization using data-driven methods.
6/2/2026
Privacy Policy Enforcement Guardrails for Data-Sensitive Retrieval-Augmented Generation
Framework for enforcing privacy policies in RAG systems using density estimators to prevent PII leakage.
6/2/2026
Balancing Knowledge Distillation for Imbalance Learning with Bilevel Optimization
Research on knowledge distillation with bilevel optimization for imbalanced learning scenarios.
6/2/2026
Lying Is Just a Phase: The Hidden Alignment Transition in Language Model Scaling
Research paper identifying phase transition in LLM scaling where reasoning and truthfulness shift from anticorrelated to cooperative behavior.
6/2/2026
Can Vision Models Truly Forget? Mirage: Representation-Level Certification of Visual Unlearning
Mirage representation-level auditing framework for certifying visual unlearning in federated learning contexts.
6/2/2026
Co-Fusion4D: Spatio-temporal Collaborative Fusion for Robust 3D Object Detection
Co-Fusion4D framework for robust 3D object detection in autonomous driving using spatiotemporal fusion.
6/2/2026
Task-Aligned Self-Supervised Learning for Medical Image Analysis: A Systematic Review and Practical Design Guidelines
Systematic review of task-aligned self-supervised learning for medical image analysis with design guidelines.
6/2/2026
Attested Tool-Server Admission: A Security Extension to the Model Context Protocol
Security extension for Model Context Protocol enabling trust-based tool server admission for LLM agents.
6/2/2026
CRISP -- Clustering-Based Redundancy-Reduced Instance Sampling for Pathology Case Representation and Retrieval
CRISP framework for autonomous multi-WSI clustering and redundancy reduction in digital pathology case retrieval and representation.
6/2/2026
I built a GitHub App to help reviewers decide if a PR is ready to approve
GitHub App that analyzes pull request signals to help reviewers assess code readiness before approval.
6/2/2026
Codex is becoming a productivity tool for everyone
OpenAI reports Codex now has 5M+ weekly active users across professions beyond coding, automating knowledge work tasks.
6/1/2026
Constraining LLMs Just Like Users
Guide on constraining LLMs for intent analysis and extraction tasks. Discusses practical applications and limitations of LLM outputs.
6/1/2026
Implicit.js, a way for agents to do 3D design with math
Implicit.js enables AI agents and applications to perform 3D CAD design using mathematical specifications, with browser-based rendering and mesh export.
6/1/2026
Open source project contains hidden instruction for "AI" agents: delete my code
Discussion of open source community tensions regarding AI usage, including reports of hidden code deletion instructions targeting AI agents.
6/1/2026
Jenesis – A modern Java build tool
Jenesis is a modern Java build tool with modular support and JVM language integration.
6/1/2026
Hatch: Write agent rules/skills once, generate for all
Hatch generates native configuration files for multiple AI coding agents (Claude Code, OpenAI Codex, GitHub Copilot, Cursor, etc.) from a single source definition.
6/1/2026
Show HN: Dataroom – a Pi and self-hosted research harness on low-budget GPU
Dataroom: self-hosted research harness using local LLM on Raspberry Pi to autonomously build cited knowledge bases for long-horizon agent tasks.
6/1/2026
Chief economist says AI-related job losses aren't happening
Newsletter signup page about AI job losses. No substantive content.
6/1/2026
Google Seeks to Raise $80B for AI Infrastructure
News headline: Google seeks $80B funding for AI infrastructure.
6/1/2026
Remote work – not AI – has sidelined recent college graduates, research finds
Research finding: Remote work policy, not AI, is primary factor affecting recent graduate employment.
6/1/2026
Show HN: Glq LLM quantization using E8 lattice
Glq is an open-source LLM quantization library using E8 lattice compression to reduce VRAM requirements for gaming GPUs, achieving 2-bit compression.
6/1/2026
Cognitive Packets for Agent Orchestration
Academic paper proposing Cognitive Packet Switching as a concept for agent orchestration within a larger Cogentia/Fractanet framework.
6/1/2026
Show HN: Knotch – a hub-and-spoke voice agent
Knotch is a coordination engine for simultaneous voice channels that uses AI to route messages to relevant participants, designed for teams sharing live audio like kitchen lines or pit crews.