All entries

TMPO: Trajectory Matching Policy Optimization for Diverse and Efficient Diffusion Alignment

arXiv:2605.10983v1 Announce Type: cross Abstract: Reinforcement learning (RL) has shown extraordinary potential in aligning diffusion models to downstream tasks, yet most of them still suffer from sig

TMRL: Diffusion Timestep-Modulated Pretraining Enables Exploration for Efficient Policy Finetuning

DGX agent

arXiv:2605.12236v1 Announce Type: cross Abstract: Fine-tuning pre-trained robot policies with reinforcement learning (RL) often inherits the bottlenecks introduced by pre-training with behavioral clon

safetyarxiv-cs-lg

13 May 2026

Hardware

To Err Is Human; To Annotate, SILICON? Toward Robust Reproducibility in LLM Annotation

arXiv:2412.14461v4 Announce Type: replace Abstract: Unstructured text data annotation is foundational to management research. LLMs offer a cost-effective and scalable alternative to human annotation,

hardwarearxiv-cs-cl

Today we release Token Superposition Training (TST), a modification to the standard LLM pretraining loop that produces a 2-3× wall-clock spe…

Today we release Token Superposition Training (TST), a modification to the standard LLM pretraining loop that produces a 2-3× wall-clock speedup at matched FLOPs without changing the model architectur

researchnous-research--x

TokenRatio: Principled Token-Level Preference Optimization via Ratio Matching

arXiv:2605.12288v1 Announce Type: new Abstract: Direct Preference Optimization (DPO) is a widely used RL-free method for aligning language models from pairwise preferences, but it models preferences o

TOPPO: Rethinking PPO for Multi-Task Reinforcement Learning with Critic Balancing

model-releasesarxiv-cs-lg

arXiv:2605.11473v1 Announce Type: cross Abstract: Soft Actor-Critic (SAC) and its variants dominate Multi-Task Reinforcement Learning (MTRL) due to their off-policy sample efficiency, while on-policy

Towards Affordable Energy: A Gymnasium Environment for Electric Utility Demand-Response Programs

arXiv:2605.12462v1 Announce Type: cross Abstract: Extreme weather and volatile wholesale electricity markets expose residential consumers to catastrophic financial risks, yet demand response at the di

applicationsarxiv-cs-lg

Towards Fine-Grained Code-Switch Speech Translation with Semantic Space Alignment

arXiv:2511.10670v2 Announce Type: replace Abstract: Code-switching (CS) speech translation (ST) aims to translate speech that alternates between multiple languages into a target language text, posing

Towards Order Fairness: Mitigating LLMs Order Sensitivity through Dual Group Advantage Optimization

arXiv:2605.11974v1 Announce Type: new Abstract: Large Language Models (LLMs) suffer from order bias, where their performance is affected by the arrangement order of input elements. This unfairness lim

Towards Uncertainty-Aware Federated Granger Causal Learning

arXiv:2602.13004v2 Announce Type: replace Abstract: Granger causality recovers directed interactions from time-series data, but in many distributed systems, the data are vertically partitioned across

applicationsarxiv-cs-lg

Towards Visually-Guided Movie Subtitle Translation for Indic Languages

arXiv:2605.11993v1 Announce Type: new Abstract: Movie subtitle translation is inherently multimodal, yet text-only systems often miss visual cues needed to convey emotion, action, and social nuance, e

applicationsarxiv-cs-cl

Toxicity Detection Should Measure Contextual Harm, Not Text-Intrinsic Badness

arXiv:2503.16072v4 Announce Type: replace-cross Abstract: Toxicity detection has become core safety infrastructure for online moderation, dataset filtering, and deployed language-model systems. Yet mo

TRACE: Temporal Routing with Autoregressive Cross-channel Experts for EEG Representation Learning

arXiv:2605.11380v1 Announce Type: new Abstract: Learning transferable representations for electroencephalography (EEG) remains challenging because EEG signals are inherently multi-channel and non-stat

researcharxiv-cs-lg

Training-Inference Consistent Segmented Execution for Long-Context LLMs

arXiv:2605.11744v1 Announce Type: new Abstract: Transformer-based large language models face severe scalability challenges in long-context generation due to the computational and memory costs of full-

researcharxiv-cs-cl

Training Transformers for KV Cache Compressibility

arXiv:2605.05971v2 Announce Type: replace Abstract: Long-context language modeling is increasingly constrained by the Key-Value (KV) cache, whose memory and decode-time access costs scale linearly wit

Trajectory-Agnostic Asteroid Detection in TESS with Deep Learning

model-releasesarxiv-cs-lg

arXiv:2605.12391v1 Announce Type: cross Abstract: We present a novel method for extracting moving objects from TESS data using machine learning. Our approach uses two stacked 3D U-Nets with skip conne

Trajectory First: A Curriculum for Discovering Diverse Policies

arXiv:2506.01568v3 Announce Type: replace Abstract: Being able to solve a task in diverse ways makes agents more robust to task variations and less prone to local optima. In this context, constrained

Transferable Delay-Aware Reinforcement Learning via Implicit Causal Graph Modeling

arXiv:2605.12312v1 Announce Type: new Abstract: Random delays weaken the temporal correspondence between actions and subsequent state feedback, making it difficult for agents to identify the true prop

Hardware

Transform Video Into Instantly Searchable, Actionable Intelligence with AI Agents and Skills

NVIDIA's video analytics AI agents analyze and process large volumes of video data through natural language tasks to provide critical insights , powered by vision language models, large language model

hardwarenvidia-developer

Transformer-Based Autonomous Driving Models and Deployment-Oriented Compression: A Survey

arXiv:2304.10891v2 Announce Type: replace-cross Abstract: Transformer-based models are becoming a central paradigm in autonomous driving because they can capture long-range spatial dependencies, multi

Hardware

TriBand-BEV: Real-Time LiDAR-Only 3D Pedestrian Detection via Height-Aware BEV and High-Resolution Feature Fusion

arXiv:2605.12220v1 Announce Type: new Abstract: Safe autonomous agents and mobile robots need fast real time 3D perception, especially for vulnerable road users (VRUs) such as pedestrians. We introduc

hardwarearxiv-cs-cv

Trust Region Inverse Reinforcement Learning: Explicit Dual Ascent using Local Policy Updates

arXiv:2605.11020v1 Announce Type: new Abstract: Inverse reinforcement learning (IRL) is typically formulated as maximizing entropy subject to matching the distribution of expert trajectories. Classica

Trust the Batch, On- or Off-Policy: Adaptive Policy Optimization for RL Post-Training

arXiv:2605.12380v1 Announce Type: new Abstract: Reinforcement learning is structurally harder than supervised learning because the policy changes the data distribution it learns from. The resulting fr

Tools

Trusted Sources for Deployment Protection

Vercel introduced a trusted sources feature for deployment protection that allows teams to control which sources can trigger deployments, enhancing security by restricting deployment access to verifie

toolsvercel-blog

Local Ai

Try the workflow: https://links.comfy.org/4daCkEY

This post likely shares a workflow link from ComfyUI, a node-based interface for AI image generation and processing. Users can access and import the workflow through the provided link to use it in the

local-aicomfyui--x

Local Ai

trying more serious TNG content with LTX2.3

local-air-stablediffusion

A user experiments with serious Star Trek: The Next Generation styled video content using LTX-2.3, a video generation model with available LoRA style adapters. LTX-2.3 is a major upgrade to video gene

Tutorials

TST has two moving parts that can be ablated independently: the input-side averaging and the output-side multi-hot cross-entropy. Both, on t…

tutorialsnous-research--x

TST has two moving parts that can be ablated independently: the input-side averaging and the output-side multi-hot cross-entropy. Both, on their own, outperform the matched-FLOPs baseline. Their effec

TST works in two phases. In phase 1, which covers the first 20-40% of training, the model reads contiguous bags of k tokens, with input embe…

TST works in two phases. In phase 1, which covers the first 20-40% of training, the model reads contiguous bags of k tokens, with input embeddings averaged within each bag, and predicts the next bag o

researchnous-research--x

U-STS-LLM A Unified Spatio-Temporal Steered Large Language Model for Traffic Prediction and Imputation

model-releasesarxiv-cs-lg

arXiv:2605.11735v1 Announce Type: new Abstract: The efficient operation of modern cellular networks hinges on the accurate analysis of spatio-temporal traffic data. Mastering these patterns is essenti

UGround: Towards Unified Visual Grounding with Unrolled Transformers

arXiv:2510.03853v4 Announce Type: replace Abstract: We present UGround, a extbf{U}nified visual extbf{Ground}ing paradigm that dynamically selects intermediate layers across extbf{U}nrolled transforme

UHR-Micro: Diagnosing and Mitigating the Resolution Illusion in Earth Observation VLMs

arXiv:2605.12237v1 Announce Type: new Abstract: Vision-Language Models (VLMs) increasingly operate on ultra-high-resolution (UHR) Earth observation imagery, yet they remain vulnerable to a severe scal

Industry

UK chip startup Fractile raised a $220M Series B led by Factorial Funds, Accel and Founders Fund to make specialized logic and memory chips for inference (Robbie Whelan/Wall Street Journal)

Robbie Whelan / Wall Street Journal: UK chip startup Fractile raised a $220M Series B led by Factorial Funds, Accel and Founders Fund to make specialized logic and memory chips for inference — Factori

industrytechmeme

Understanding and Preventing Entropy Collapse in RLVR with On-Policy Entropy Flow Optimization

arXiv:2605.11491v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR) has become an effective paradigm for improving the reasoning ability of large language models. How

Understanding Sample Efficiency in Predictive Coding

arXiv:2605.11911v1 Announce Type: new Abstract: Predictive Coding (PC) is an influential account of cortical learning. Much of recent work has focused on comparing PC to Backpropagation (BP) to find w

Understanding the Performance Gap in Preference Learning: A Dichotomy of RLHF and DPO

arXiv:2505.19770v5 Announce Type: replace-cross Abstract: We present a fine-grained theoretical analysis of the performance gap between two-stage reinforcement learning from human feedback~(RLHF) and

UnfoldLDM: Degradation-Aware Unfolding with Iterative Latent Diffusion Priors for Blind Image Restoration

arXiv:2511.18152v3 Announce Type: replace Abstract: Deep unfolding networks (DUNs) combine the interpretability of model-based methods with the learning ability of deep networks, yet remain limited fo

Tutorials

UniCustom: Unified Visual Conditioning for Multi-Reference Image Generation

arXiv:2605.12088v1 Announce Type: new Abstract: Multi-reference image generation aims to synthesize images from textual instructions while faithfully preserving subject identities from multiple refere

tutorialsarxiv-cs-cv

UniFixer: A Universal Reference-Guided Fixer for Diffusion-Based View Synthesis

arXiv:2605.12169v1 Announce Type: new Abstract: With the recent surge of generative models, diffusion-based approaches have become mainstream for view synthesis tasks, either in an explicit depth-warp

Uniform Scaling Limits in AdamW-Trained Transformers

arXiv:2605.11059v1 Announce Type: cross Abstract: We study the large-depth limit of transformers trained with AdamW, by modelling the hidden-state dynamics as an interacting particle system (IPS) coup

researcharxiv-cs-lg

UniVLR: Unifying Text and Vision in Visual Latent Reasoning for Multimodal LLMs

arXiv:2605.11856v1 Announce Type: cross Abstract: Multimodal large language models are increasingly expected to perform thinking with images, yet existing visual latent reasoning methods still rely on

applicationsarxiv-cs-cl

Unlearning with Asymmetric Sources: Improved Unlearning-Utility Trade-off with Public Data

arXiv:2605.11170v1 Announce Type: new Abstract: Noise-based certified machine unlearning currently faces a hard ceiling: the noise magnitude required to certify unlearning typically destroys model uti

researcharxiv-cs-lg

Unlocking Compositional Generalization in Continual Few-Shot Learning

arXiv:2605.11710v1 Announce Type: cross Abstract: Object-centric representations promise a key property for few-shot learning: Rather than treating a scene as a single unit, a model can decompose it i

researcharxiv-cs-cv

Agents

Unlocking LLM Creativity in Science through Analogical Reasoning

arXiv:2605.11258v1 Announce Type: cross Abstract: Autonomous science promises to augment scientific discovery, particularly in complex fields like biomedicine. However, this requires AI systems that c

agentsarxiv-cs-cl

Unlocking UML Class Diagram Understanding in Vision Language Models

arXiv:2605.11634v1 Announce Type: new Abstract: Although Vision Language Models (VLMs) have seen tremendous progress across all kinds of use cases, they still fall behind in answering questions regard

Unpacking the Eye of the Beholder: Social Location, Identity, and the Moving Target of Political Perspectives

arXiv:2605.11166v1 Announce Type: new Abstract: Political and social identities structure how people evaluate political information, a finding decades deep in political science and routinely discarded

researcharxiv-cs-cv

Urban Risk-Aware Navigation via VQA-Based Event Maps for People with Low Vision

arXiv:2605.11782v1 Announce Type: new Abstract: Visual impairment affects hundreds of millions of people worldwide, severely limiting their ability to navigate urban environments safely and independen

USEMA: a Scalable Efficient Mamba Like Attention for Medical Image Segmentation

arXiv:2605.11131v1 Announce Type: new Abstract: Accurate medical image segmentation is an integral part of the medical image analysis pipeline that requires the ability to merge local and global infor

researcharxiv-cs-cv

Local Ai

v0.23.4

Ollama v0.23.4 is a release version of Ollama, a tool for running large language models locally. This patch release likely includes bug fixes, performance improvements, and refinements to existing fea

local-aiollama-releases