arXiv AI
Jun 2
Neural Network Compression by Approximate Differential Equivalence
arXiv:2606. 01402v1 Announce Type: cross Abstract: Neural network compression is commonly achieved by pruning parameters based on local importance scores, e.
Benchmarks and evaluation
Leaderboards, eval harnesses and ablations — the contested business of deciding which model is actually better.
arXiv AI
Jun 2
Evaluating Deep Research Agents on Expert Consulting Work: A Benchmark with Verifiers, Rubrics, and Cognitive Traps
arXiv:2605. 17554v2 Announce Type: replace Abstract: Frontier deep research agents (DRAs) plan a research task, synthesize across documents, and return a structured deliverable on demand.
arXiv AI
Jun 2
FrontierOR: Benchmarking LLMs' Capacity for Efficient Algorithm Design in Large-Scale Optimization
arXiv:2605. 25246v3 Announce Type: replace Abstract: Large language models (LLMs) are increasingly used for optimization modeling and solver-code generation, yet practical operations research and optimization problems often require a harder capability: designing scalable algorithms that exploit problem structure and outperform direct formulation-and-solve baselines.
arXiv AI
Jun 2
STaR-KV: Spatio-Temporal Adaptive Re-weighting for KV Cache Compression in GUI Vision-Language Models
arXiv:2606. 01790v1 Announce Type: cross Abstract: Vision-language-model-based graphical user interface (GUI) agents have shown broad automation capabilities, yet deployment is bottlenecked by a key-value (KV) cache that grows linearly with interaction steps.
arXiv AI
Jun 2
Recent Advances in Multi-modal 3D Intelligence: A Comprehensive Survey and Evaluation
arXiv:2310. 15676v2 Announce Type: replace-cross Abstract: Multi-modal 3D Intelligence has gained considerable attention due to its wide applications in autonomous driving and world simulation, etc.
arXiv AI
Jun 2
Graph is a Natural Regularization: Revisiting Vector Quantization for Graph Representation Learning
arXiv:2508. 06588v3 Announce Type: replace-cross Abstract: Vector Quantization (VQ) has recently emerged as a promising approach for learning compressed and discrete representations for graph-structured data.
arXiv AI
Jun 2
From Segments to Scenes: Temporal Understanding in Autonomous Driving via Vision-Language Model
arXiv:2512. 05277v3 Announce Type: replace-cross Abstract: Vision-Language Models (VLMs) are increasingly deployed as the perception and reasoning backbone of autonomous agents acting in the wild, with autonomous driving (AD) being one of the most safety-critical instances.
arXiv AI
Jun 2
NILC: Discovering New Intents with LLM-assisted Clustering
arXiv:2511. 05913v2 Announce Type: replace-cross Abstract: New intent discovery (NID) seeks to recognize both new and known intents from unlabeled user utterances, which finds prevalent use in practical dialogue systems.
arXiv AI
Jun 2
PR2: Predictive Routing Replay for MoE-Based LLM Reinforcement Learning
arXiv:2606. 00395v1 Announce Type: cross Abstract: Mixture of Experts (MoE) Large Language Models (LLMs) achieve strong performance at scale.
arXiv AI
Jun 2
Mitigating Hallucinations in Large Language Models Via Decoder Layer Skipping
arXiv:2606. 00819v1 Announce Type: new Abstract: Large Language Models (LLMs) have achieved strong performance across diverse natural language tasks, yet their outputs often suffer from hallucinations -- content that is misaligned with factual information.
arXiv AI
Jun 2
ForeSci: Evaluating LLM Agents for Forward-Looking AI Research Judgment
arXiv:2606. 00644v1 Announce Type: new Abstract: AI research often requires decisions before future evidence exists: which bottleneck to attack, which direction to pursue, or where a project should be positioned.
arXiv AI
Jun 2
Lying Is Just a Phase: The Hidden Alignment Transition in Language Model Scaling
arXiv:2605. 18838v3 Announce Type: replace-cross Abstract: Scaling laws predict loss from compute but not how capabilities interact.
arXiv AI
Jun 2
Product-Aware Deep Autoencoders for Robust Process Monitoring in Multi-Product Cyber-Physical Systems
arXiv:2606. 00052v1 Announce Type: new Abstract: As Industry 4.
arXiv AI
Jun 2
MESA: Improving MoE Safety Alignment via Decentralized Expertise
arXiv:2606. 00651v1 Announce Type: cross Abstract: Mixture-of-Experts (MoE) architectures scale Large Language Models (LLMs) efficiently, enabling greater capacity with reduced computational cost by dynamically routing inputs to relevant experts, yet introduce a critical vulnerability: Safety Sparsity, where safety capabilities concentrate in few experts, making them susceptible to adversarial bypassing.
arXiv AI
Jun 2
Stop Wandering, Find the Keys: LLMs Discriminate Key States for Efficient Multi-Agent Exploration
arXiv:2410. 02511v2 Announce Type: replace Abstract: With expansive state-action spaces, efficient multi-agent exploration remains a longstanding challenge in reinforcement learning.
arXiv AI
Jun 2
Behavior-Invariant Task Representation Learning with Transformer-based World Models for Offline Meta-Reinforcement Learning
arXiv:2606. 00780v1 Announce Type: cross Abstract: Offline meta-reinforcement learning leverages static datasets to enable agents to generalize to unseen environments by combining offline efficiency with meta-learning adaptability, yet it faces key challenges from context and policy distribution shifts.
arXiv AI
Jun 2
Zamba2-VL Technical Report
arXiv:2606. 00390v1 Announce Type: cross Abstract: We present Zamba2-VL, a suite of vision-language models built on Zamba2, a hybrid language-model architecture combining Mamba2 state-space layers with a small number of shared transformer blocks.
arXiv AI
Jun 2
AgentRedBench: Dynamic Redteaming and Integration-Aware Defense for LLM Agents over SaaS Integrations
arXiv:2606. 02240v1 Announce Type: cross Abstract: Indirect prompt injection in tool-use agents is a concrete production threat: LLM agents read from integrations (third-party services such as Gmail, Salesforce, or Jira accessed through tool calls) whose response content the user neither writes nor controls.
arXiv AI
Jun 2
Versatile Framework with Semantic and Structural guidance for Image Reconstruction from Brain Activity
arXiv:2606. 00121v1 Announce Type: cross Abstract: Reconstructing visual stimuli from brain recordings has been a meaningful and challenging task in brain decoding.
arXiv AI
Jun 2
Low-Resource Safety Failures Are Action Failures, Not Representation Failures
arXiv:2606. 01196v1 Announce Type: cross Abstract: Safety alignment learned in high-resource languages transfers poorly to low-resource languages.