July 2026

8 Jul

arxiv.org

machine-learning

EquiFiLM: Charge-Conditioned Equivariant Force Fields via Feature-wise Linear Modulation

8 Jul

machinebrief.com

machine-learning

Low-Overhead Error-Corrected QCNNs Using Bivariate Bicycle Codes

8 Jul

arxiv.org

large-language-models

From Passive Retrieval to Active Memory Navigation: Learning to Use Memory as a Structured Action Space

8 Jul

arxiv.org

large-language-models

Onnes: A Physics-Grounded Multi-Agent LLM Simulator for Cryogenic Fault Diagnosis in Quantum Computing Infrastructure

8 Jul

arxiv.org

ai-agents

StateFuse: Deterministic Conflict-Preserving Memory for Multi-Agent Systems

8 Jul

arxiv.org

computer-vision

A Task-Driven Evaluation of UAV Detection and Tracking under Synthetic Fog

8 Jul

arxiv.org

computer-vision

Recovering Cloud Microstructures with Cascaded Diffusion Inversion

8 Jul

arxiv.org

computer-vision

Robust Face Super-Resolution and Recognition Through Multi-Feature Aggregation in Diffusion Models

8 Jul

arxiv.org

large-language-models

Ground3D-LMM: Fine-Grained 3D Point Grounding and Spatial Reasoning with LMM

8 Jul

arxiv.org

artificial-intelligence

Light-Omni: Reflex over Reasoning in Agentic Video Understanding with Long-Term Memory

8 Jul

arxiv.org

large-language-models

How Personas Can Influence Agents to Play Split or Steal

8 Jul

arxiv.org

large-language-models

Most LLM Conformity Needs No Speaker: Measuring the Speaker-Free Floor in Peer-Pressure Benchmarks

8 Jul

arxiv.org

large-language-models

Benchmarking KV-Cache Optimizations across Task Quality and System Performance for Long-Context Serving

8 Jul

arxiv.org

machine-learning

Text Distance from Nested and Hierarchical Repetitions: A Compression-Based Perspective

8 Jul

arxiv.org

large-language-models

Prompt Robustness Is Task-Dependent: Comparing Objective and Belief-Style Questions in LLM Evaluation

8 Jul

arxiv.org

large-language-models

ResonatorLM: Causal Resonant Field Mixing for Efficient Long-Context Language Modelin

8 Jul

arxiv.org

large-language-models

Revisiting the Relation Between Language Model Perplexity and ASR Word Error Rate for Modern End-to-End Speech Recognition

8 Jul

arxiv.org

large-language-models

BaFCo: A Document Understanding Benchmark for Complex Bangla Form Comprehension

8 Jul

arxiv.org

large-language-models

RPAM: A Principled Metric for Evaluating Associations in Language Models with High Predictive Validity in Downstream Outputs

8 Jul

arxiv.org

natural-language-processing

Where to cut, how deep: BPE and Unigram-LM on chemistry SMILES

8 Jul

arxiv.org

large-language-models

Narrative World Model: Narratology-Grounded Writer Memory for Long-Form Fiction

8 Jul

arxiv.org

large-language-models

FirstResearch: Auditable Question Formation for LLM Scientific Discovery Agents

8 Jul

arxiv.org

computer-vision

Rendering-Aware Bayesian 3D Gaussian Splatting with Native Uncertainty and Adaptive Complexity Control

8 Jul

arxiv.org

large-language-models

Akashic: A Low-Overhead LLM Inference Service with MemAttention

8 Jul

arxiv.org

artificial-intelligence

ArtisanCAD: An Industrial-Level CAD Agent with Expert-Grounded Knowledge Distillation

8 Jul

arxiv.org

large-language-models

Beyond Static Evaluation: Building Simulation Environments for Scalable Agentic Reinforcement Learning

8 Jul

arxiv.org

large-language-models

Controlling Tool Use with Heading-Specific Activation Steering

8 Jul

arxiv.org

machine-learning

TurnOPD: Making On-Policy Distillation Turn-Aware for Efficient Long-Horizon Agent Training

8 Jul

arxiv.org

machine-learning

Multi-Teacher Contrastive Distillation for Edge-Efficient Pathology Foundation Models

8 Jul

arxiv.org

machine-learning

Uncovering Latent Depression Severity for Binary Depression Detection via Advantage-weighting Ranking