Papersby Glyph

Notable data and AI papers

Papers627 Labs45

627 papers · 45 labs

TOPReward: Token Probabilities as Hidden Zero-Shot Rewards for Robotics research paper by Ai2, 2026

Ai2 · Inference and efficiency · Feb 22, 2026 · 43 citations · 26 upvotes · unverified

TOPReward is a probabilistically grounded temporal value function that uses pretrained video Vision-Language Models to estimate robotic task progress through internal token logits, achieving superior performance in zero-shot evaluations across diverse real-world tasks.

By Shirui Chen, Cole Harrison, Ying-Chun Lee and 6 more · arXiv 2602.19313 · PDF · Code

UnverifiedHugging Face's summary; not yet checked by hand.

More from Ai2

Multimodal and roboticsUnverifiedJun 17, 2026MolmoMotion: Forecasting Point Trajectories in 3D with Language Instruction3D point motion forecasting model predicts object trajectories from visual history and language goals, demonstrating superior performance on benchmarks and transferring effectively to robot manipulation and video generation tasks.

Ai216 citations53 upvotesRead →Multimodal and roboticsMay 4, 2026MolmoAct2: Action Reasoning Models for Real-world DeploymentA fully open robot action model, released with new datasets including 720 hours of two-arm teleoperation.

Ai2100 citations355 upvotesRead →Multimodal and roboticsUnverifiedApr 9, 2026WildDet3D: Scaling Promptable 3D Detection in the WildA unified 3D object detection framework with a large-scale dataset enables open-world detection with multiple prompt types and geometric cue integration.

Ai215 citations95 upvotesRead →ReasoningUnverifiedFeb 8, 2026Recurrent-Depth VLA: Implicit Test-Time Compute Scaling of Vision-Language-Action Models via Latent Iterative ReasoningRD-VLA introduces a recurrent architecture for vision-language-action models that adapts computational depth through latent iterative refinement, achieving constant memory usage and improved task success rates.

Ai221 citations71 upvotesRead →ReasoningUnverifiedDec 15, 2025Olmo 3Olmo 3, a family of state-of-the-art fully-open language models at 7B and 32B parameter scales, excels in long-context reasoning, function calling, coding, instruction following, general chat, and knowledge recall.

Ai237 upvotesRead →ReasoningUnverifiedAug 11, 2025MolmoAct: Action Reasoning Models that can Reason in SpaceAction Reasoning Models (ARMs) integrate perception, planning, and control to enable adaptable and explainable robotic behavior, achieving superior performance across various tasks and settings.

Ai2232 citations45 upvotesRead →

Inference and efficiencySep 12, 2023Efficient Memory Management for Large Language Model Serving with PagedAttentionvLLM manages the KV cache like pages of virtual memory, serving models with 2 to 4 times the throughput.

UC Berkeley9,965 citations72 upvotesRead →Inference and efficiencyMay 27, 2022FlashAttention: Fast and Memory-Efficient Exact Attention with IO-AwarenessFlashAttention computes exact attention with far fewer GPU memory reads and writes, making long sequences faster.

Stanford University5,830 citations16 upvotesRead →Inference and efficiencyUnverifiedJul 24, 2025Group Sequence Policy OptimizationGroup Sequence Policy Optimization (GSPO) is a reinforcement learning algorithm that improves training efficiency and performance of large language models by using sequence-level importance ratios and operations.

Alibaba (Qwen)814 citations323 upvotesRead →Inference and efficiencyUnverifiedFeb 16, 2025Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse AttentionNSA, a trainable sparse attention mechanism, enhances long-context modeling efficiency without sacrificing performance, achieving improvements in speed and accuracy over full attention models.

DeepSeek596 citations157 upvotesRead →Inference and efficiencyUnverifiedApr 7, 2025SmolVLM: Redefining small and efficient multimodal modelsSmolVLM, a series of compact multimodal models, achieves high performance with minimal GPU memory usage, making efficient deployment on mobile and edge devices possible.

Hugging Face330 citations212 upvotesRead →Inference and efficiencyUnverifiedOct 17, 2025Chronos-2: From Univariate to Universal ForecastingChronos-2, a pretrained model with a group attention mechanism, achieves state-of-the-art performance in zero-shot univariate, multivariate, and covariate-informed forecasting tasks.

Amazon276 citations28 upvotesRead →

About this paper

Venue: arXiv.org
Citations: 43, 7 influential · Semantic Scholar
Upvotes: 26 · Hugging Face
Lab: Ai2 · on Companies · on blogs · on labs · on Leaders · on Paydays · on problems · on Releases · on repos · on socials · on standards · on terms · on Titlewave

Changes

CitationsNov 2, 2026Citations rose from 37 to 43.

CitationsOct 12, 2026Citations rose from 35 to 37.

CitationsOct 5, 2026Influential citations rose from 6 to 7.

CitationsOct 5, 2026Citations rose from 28 to 35.

CitationsSep 25, 2026A first count of 6 influential citations.

CitationsSep 25, 2026A first count of 28 citations.

New paperSep 25, 2026Found by the weekly Hugging Face scan; not yet checked by hand.