Research Feed Page 45

Search source-linked summaries of recent AI and machine-learning papers by topic, by date, or by whether they include code or a diagram.

Filter papers All papers

Browse by date

Resource filters

Sort options

Research results

Reinforcement Learning By Aniruddhan Ganesaraman 2026-07-16
Data Driven Block Replacement Scheduling

The paper presents data-driven algorithms to determine the optimal interval for replacing machine parts when their lifetime distribution is unknown.

Efficiency & Inference By Arthur G. Bubolz 2026-07-16
Decoding Market Emotion from Blockchain Activity: A Data-Driven Sentiment Classifier

The paper presents a sentiment classifier that integrates daily Bitcoin on-chain metrics with Twitter sentiment analysis to identify market phases.

Multimodal / Efficiency & Inference By Binghui Chen 2026-07-16
WanSong v1.0 Technical Report

WanSong v1.0 is a music generation model that uses a hybrid transformer architecture and a dual-stem output strategy to improve the fidelity and separation of vocals and background music.

Agents / Safety & Alignment By Weimeng Wang 2026-07-16
When Words Are Safe But Actions Kill: Probing Physical Danger Beyond Text Safety in Hidden-State Risk Space

The paper introduces a probing technique that detects when LLM-generated instructions pose physical risks despite appearing linguistically safe.

Efficiency & Inference / Training & Fine-Tuning By Jimmy T. H. Smith 2026-07-16
In-Place Tokenizer Expansion for Pre-trained LLMs

This paper presents an in-place recipe to expand pre-trained model tokenizers to better support underrepresented languages without discarding existing model weights.

Efficiency & Inference By Hector J. Garcia 2026-07-16
Mutable Low-Rank Sketches for Retrain-Free Recommendation

The authors introduce a mutable sketch method that updates user preferences in log-time to allow for real-time recommendations without needing to retrain the entire model.

Agents / Benchmarks & Evals By Paul Kassianik 2026-07-16
Beyond Success Rate: Cost-Aware Evaluation of Offensive and Defensive Security Agents

The paper introduces a cost evaluation framework for security agents that measures economic efficiency alongside performance on offensive and defensive benchmarks.

Computer Vision / Efficiency & Inference By Baback Elmieh 2026-07-16
Online Neural Space Time Memory for Dynamic Novel View Synthesis

The paper introduces Online Neural Space Time Memory to enable persistent, long-horizon novel view synthesis for streaming video without the computational overhead of per-frame updates.

Computer Vision / Efficiency & Inference By Zizhao Chen 2026-07-16
From Draft to Draft-Free: One-Step Video Object Removal via Privileged Distillation and Fast Planting

The researchers developed a model that performs video object removal in a single inference step by eliminating the need for external draft priors.

Benchmarks & Evals By Leanne Tan 2026-07-16
Project Kaleidoscope: Contextual, Human-Aligned Evaluation for Real-World AI Applications

Project Kaleidoscope introduces a workflow for calibrating automated LLM judges against human labels to evaluate real world AI applications.

Agents / Reinforcement Learning By Jinyang Wu 2026-07-16
SEED: Self-Evolving On-Policy Distillation for Agentic Reinforcement Learning

The paper introduces a method called SEED that improves agentic performance by having the model analyze its own past trajectories to generate dense feedback for training.

Multimodal / Efficiency & Inference By Xinhao Li 2026-07-16
VideoChat3: Fully Open Video MLLM for Efficient and Generalist Video Understanding

VideoChat3 is an open-source video language model that improves generalization and computational efficiency for video understanding tasks through a specialized 3D visual architecture and multi-stage instruction tuning.

Multimodal / Agents By Lianghua Huang 2026-07-16
Video = World + Event Stream

The paper introduces Wan-Streamer v0.3 to enable a general-purpose pretraining objective for native-streaming generation by reframing video as a world plus an event stream.

Robotics / Safety & Alignment By Qi Li 2026-07-16
BadWAM: When World-Action Models Dream Right but Act Wrong

The BadWAM framework exposes vulnerabilities in world-action models by using black-box optimization to force robots into task-failing actions via small visual perturbations.

Agents / Benchmarks & Evals By Yuyao Zhang 2026-07-16
SearchOS-V1: Towards Robust Open-Domain Information-Seeking Agent Collaboration

SearchOS-V1 is a framework that improves information-seeking tasks by externalizing search state and coordinating agents through shared persistent artifacts.

Reinforcement Learning / Efficiency & Inference By Yushi Huang 2026-07-16
MeanFlowNFT: Bringing Forward-Process RL to Average-Velocity Generators

MeanFlowNFT introduces a method to apply reinforcement learning to MeanFlow generators by creating an induced instantaneous velocity predictor to define reward optimization.

Robotics / Efficiency & Inference By Yunfan Jiang 2026-07-16
RoboTTT: Context Scaling for Robot Policies

The researchers developed RoboTTT to enable robots to handle long sequences of actions by storing historical context through integrated test-time training layers.

Multimodal / Benchmarks & Evals By Pengcheng Zhou 2026-07-16
HoloGeo: Mitigating Landmark Bias in Geo-localization via Evidence-Driven Reasoning

HoloGeo is a framework that improves image geo-localization accuracy by training models to reason beyond superficial visual landmarks using evidence-driven reinforcement learning.

Agents / Efficiency & Inference By Amirhosein Ghasemabadi 2026-07-15
Multi-Head Latent Control: A Unified Interface for LLM Agent Decision Making

The paper introduces a lightweight interface that allows frozen foundation models to dynamically decide when to handle tasks independently or delegate to a stronger fallback model.

Benchmarks & Evals / Computer Vision By Scott H. Hawley 2026-07-16
MIDI-RAE-JEPA: Hierarchical Representation Learning and Generation for Symbolic Music

The paper introduces MIDI-RAE-JEPA, a model that learns hierarchical music representations by treating piano rolls as images and enforcing geometric constraints on latent space.