Latest AI/ML research from ArXiv and Papers with Code
Sparse autoencoders (SAEs) are widely used to interpret neural network representations, but their utility depends on whether the learned features are reproducible across training r...
Spatial reasoning from egocentric videos is inherently challenging because the observable evidence is constrained by the camera trajectory. Existing methods rely on single-turn inf...
Router is the cornerstone component to the Mixture-of-Experts models. Serving as expert proxies, the rows of the router matrix compute their similarity to the MoE inputs to determi...
The recent success of agent swarms has shifted the paradigm of large language model (LLM)-based agents from single-agent workflows to multi-agent systems, highlighting the importan...
General-purpose agents such as OpenClaw are increasingly used as autonomous tool users, but their coding ability is difficult to measure under SWE-bench: a generic agent does not b...
Anticipating LLM behavioral tendencies from low-cost psychometric probes is critical for safe deployment, but only if self-reports (SR) reliably predict behavior. Recent work docum...
Vision-language models (VLMs) project images into hundreds to thousands of visual tokens, making decoder inference expensive in both attention computation and KV-cache memory. Exis...
Large language models (LLMs) are widely used to tackle complex tasks with autonomous workflows. Recently, reusable natural language skills have emerged as a popular paradigm to inj...
The Network Data Analytics Function (NWDAF) is central to enabling zero-touch network management in fifth-generation (5G) networks by supporting real-time analytics and closed-loop...
Remaining Useful Life (RUL) prediction is essential for industrial predictive maintenance, yet many learning-based approaches rely on extensive feature engineering or large labeled...
Multimodal image fusion aims to integrate complementary information from different modalities into a fused image that preserves rich local details while maintaining globally consis...
Speculative decoding (SD) addresses the high inference costs of LLMs by having lightweight drafters generate candidates for large verifiers to validate in parallel. Existing draft-...
Learning compatible representations aims to learn feature representations that can be used interchangeably over time whenever a model undergoes updates. In this paper, we demonstra...
Environments serve as interactive systems for large language model (LLM) based agents across diverse scenarios and play a crucial role in driving the continual evolution of model c...
Recent progress in foundation models has shifted toward agentic behavior involving multi-step reasoning and tool use. However, open-source efforts largely focus on text-dominant se...
Expressive performance rendering (EPR) aims to generate realistic performances constrained on sequences of notes. However, flow matching audio editing models manipulate only synchr...
Pretrained video generators are promising visual world models that exhibit emergent task-solving abilities; however, their reliance on detailed textual descriptions limits their di...
Reinforcement learning (RL) has become a key component in modern large language models, yet the rollout stage remains the key bottleneck in RL training pipelines. Although Multi-To...
Few-step diffusion distillation has become increasingly mature for 4-8-step generation, yet pushing further to 2 steps remains challenging. In this work, we introduce Z-Image Turbo...
Vision-Language-Action (VLA) models inherit semantic grounding from large-scale pretraining and perform competently across in-distribution manipulation tasks. This grounding, howev...
Large Language Models (LLMs) offer new potential for translation tasks but often experience performance degradation when handling low-resource languages. To address this limitation...
Finding interpretable directions in language-model representations is critical for understanding and controlling model behavior. Sparse autoencoders (SAEs) have become the standard...
Compact language models (LMs) reduce cost, latency, and deployment risk for tool agents. Yet MCP-style tool use requires more than isolated function calling: an agent must discover...
AI agents are increasingly being developed to accelerate scientific discovery, yet their practical capabilities in real research settings remain poorly understood. Existing benchma...