Online Finetuning Decision Transformers with Pure RL Gradients

⋅

arXiv:2601.00167v1 Announce Type: new Abstract: Decision Transformers (DTs) have emerged as a powerful framework for sequential decision making by formulating offline reinforcement learning (RL) as a sequence modeling problem. However, extending DTs to online settings with pure RL gradients remains largely unexplored, as existing approaches continue to rely heavily on supervised sequence-modeling objectives during online finetuning. We identify hindsight return relabeling — a standard component in online DTs — as a critical obstacle to RL-based finetuning: while beneficial […]

Ver mais

Liked Liked
The State of Reinforcement Learning for LLM Reasoning

The State of Reinforcement Learning for LLM Reasoning

⋅

A lot has happened this month, especially with the releases of new flagship models like GPT-4.5 and Llama 4. But you might have noticed that reactions to these releases were relatively muted. Why? One reason could be that GPT-4.5 and Llama 4 remain conventional models, which means they were trained without explicit reinforcement learning for reasoning. Meanwhile, competitors such as xAI and Anthropic have added more reasoning capabilities and features into their models. For instance, both the xAI […]

Ver mais

Liked Liked

LLMDiRec: LLM-Enhanced Intent Diffusion for Sequential Recommendation

⋅

arXiv:2601.03259v1 Announce Type: new Abstract: Existing sequential recommendation models, even advanced diffusion-based approaches, often struggle to capture the rich semantic intent underlying user behavior, especially for new users or long-tail items. This limitation stems from their reliance on ID-based embeddings, which lack semantic grounding. We introduce LLMDiRec, a new approach that addresses this gap by integrating Large Language Models (LLMs) into an intent-aware diffusion model. Our approach combines collaborative signals from ID embeddings with rich semantic representations from […]

Ver mais

Liked Liked

ICSA Unveils 25th Connected Banking Summit in Accra

⋅

Accra, Ghana – The International Centre for Strategic Alliances (ICSA) proudly announces the 25th Edition Connected Banking Summit – Innovation & Excellence Awards 2026, taking place on 25th February 2026 in Accra, Ghana. Marking a historic Silver Jubilee milestone, the summit returns to Accra where it all began in 2018 to bring together senior banking leaders, fintech innovators, regulators, and technology strategists to accelerate West Africa’s financial sector transformation. Under the theme “Next-Gen Finance West Africa: Resilient, Scalable […]

Ver mais

Liked Liked

Model-Free Monte Carlo-like Policy Evaluation

⋅

We propose an algorithm for estimating the finite-horizon expected return of a closed loop control policy from an a priori given (off-policy) sample of one-step transitions. It averages cumulated rewards along a set of “broken trajectories” made of one-step transitions selected from the sample on the basis of the control policy. Under some Lipschitz continuity assumptions on the system dynamics, reward function and control policy, we provide bounds on the bias and variance of the estimator that depend […]

Ver mais

Liked Liked
Introducing aiclient-llm: One Python Client for All Your LLMs

Introducing aiclient-llm: One Python Client for All Your LLMs

⋅

Introducing Aiclient-LLM: One Python Client for All Your LLMs The unified, minimal, and production-ready Python SDK for OpenAI, Anthropic, Google Gemini, xAI, and local LLMs — with built-in agents, resilience, and observability. aiclient banner Have you ever found yourself juggling multiple SDKs just to use different LLM providers? Writing separate code for OpenAI’s client, Anthropic’s SDK, Google’s API, and then trying to make them work together? If you’ve built production AI applications, you know the pain: different response formats, inconsistent error […]

Ver mais

Liked Liked
LAI #108: Building What Lasts in the Year Ahead

LAI #108: Building What Lasts in the Year Ahead

⋅

Author(s): Towards AI Editorial Team Originally published on Towards AI. Good morning, AI enthusiasts, and happy new year 🎉 This is the first issue of the year, and it feels like a good moment to reset expectations and direction. We’re starting 2026 by looking ahead, not at launches or demos, but at what it will actually take to build AI systems that hold up in the real world: systems that are reliable, governable, and affordable to run. We […]

Ver mais

Liked Liked

Load More

↑

Digitado © 2025