Skip to content
Papers.

Chronos-2: From Univariate to Universal Forecasting research paper by Amazon, 2025

Amazon · Oct 17, 2025 · Inference and efficiency · 178 citations · 28 upvotes · unverified

Read on arXiv

What it shows

Chronos-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.

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

More from Amazon

All 6
PaperCitations
Don't Mask the Environment: Observation Supervision Changes How Agents Explore Under RLAgent trajectories record what an agent does and what happens next.Agents and evaluation · Sep 2026 · Unverified0
VIDEOP2R: Video Understanding from Perception to ReasoningVideoP2R, a process-aware reinforcement fine-tuning framework, improves video reasoning and understanding by modeling perception and reasoning separately, achieving state-of-the-art results on multiple benchmarks.Reasoning · Nov 2025 · Unverified9
Adaptive Multi-Agent Response Refinement in Conversational SystemsA multi-agent framework enhances conversational quality by refining responses through agents responsible for factuality, personalization, and coherence, outperforming existing methods on challenging datasets.Agents and evaluation · Nov 2025 · Unverified3
When Thoughts Meet Facts: Reusable Reasoning for Long-Context LMsThought templates enhance long-context language models by structuring evidence combination and guiding multi-hop inference, leading to consistent performance improvements across various benchmarks.Reasoning · Oct 2025 · Unverified3
TaTToo: Tool-Grounded Thinking PRM for Test-Time Scaling in Tabular ReasoningTaTToo, a novel table-grounded Process Reward Model, enhances tabular reasoning by explicitly addressing table-specific operations and integrating tool-based verification, leading to significant performance improvements over existing PRMs.Reasoning · Oct 2025 · Unverified12

Other inference and efficiency papers

Topic
PaperCitations
Efficient 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 Berkeley · Sep 20238,481
FlashAttention: 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 University · May 20225,334
Group 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) · Jul 2025 · Unverified688
Native 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.DeepSeek · Feb 2025 · Unverified507
SmolVLM: 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 Face · Apr 2025 · Unverified294
Inference-Time Scaling for Generalist Reward ModelingSelf-Principled Critique Tuning enhances pointwise generative reward modeling for large language models, improving scalability and quality compared to existing methods.DeepSeek · Apr 2025 · Unverified249
About this paper
Authors
Abdul Fatir Ansari, Oleksandr Shchur, Jaris Küken and 20 more
arXiv
2510.15821 · PDF
Venue
arXiv.org
Citations
178, 52 influential · Semantic Scholar
Upvotes
28 · Hugging Face
Code
github.com/amazon-science/chronos-forecasting
Lab
Amazon · on Companies · on Quarterly · on Paydays

Changes

What changed
Influential citationsfirst count: 52Sep 25, 2026
Citationsfirst count: 178Sep 25, 2026
New paperFound by the weekly scan, unverifiedSep 25, 2026

Sources: each lab's own papers and arXiv, with citation and upvote counts from Semantic Scholar and Hugging Face. One-line summaries are for orientation, not a substitute for the paper. Logos via logo.dev; trademarks belong to their owners.

New papers by email

Monday afternoons, only in weeks with new papers from the labs.

Double opt-in. Unsubscribe any time.