However, this is not always the case, as different tasks can compete with each other and lead to weaker models.

However, this is not always the case, as different tasks can compete with each other and lead to weaker models.

The manual prompt design process for LLMs at the reasoning phase is tedious and an automated prompt optimization method is desired.

Recommender systems aim to predict personalized rankings based on user preference data. With the rise of Language Models (LMs), LM-based recommenders have been widely explored due to their extensive world knowledge and powerful reasoning abilities. Most of the LM-based recommenders convert historical interactions into language prompts, pairing with a positive item as the target response and fine-tuning LM with a language modeling loss. However, the current objective fails to fully leverage preference data and is not optimized for personalized ranking tasks, which hinders the performance of LM-based recommenders. Inspired by the current advancement of Direct Preference Optimization (DPO) in human preference alignment and the success of softmax loss in recommendations, we propose Softmax-DPO (\textbf{S-DPO}) to instill ranking information into the LM to help LM-based recommenders distinguish preferred items from negatives, rather than solely focusing on positives. Specifically, we incorporate multiple negatives in user preference data and devise an alternative version of DPO loss tailored for LM-based recommenders, which is extended from the traditional full-ranking Plackett-Luce (PL) model to partial rankings and connected to softmax sampling strategies. Theoretically, we bridge S-DPO with the softmax loss over negative sampling and find that it has an inherent benefit of mining hard negatives, which assures its exceptional capabilities in recommendation tasks. Empirically, extensive experiments conducted on three real-world datasets demonstrate the superiority of S-DPO to effectively model user preference and further boost recommendation performance while providing better rewards for preferred items.

Breakthroughs, discoveries, and DIY tips sent every weekday. A newborn star 15,000 light-years from Earth is fascinating astronomers with its dual blasts of superheated plasma jets . The rare sight captured in stunning detail by the James Webb Space Telescope (JWST) isn't only a display of cosmic forces. It's helping solve a decades' long debate about the origins of massive stellar objects. Located at the edge of the Milky Way galaxy inside a nebula known as Sharpless 2-284 (Sh2-284), the young protostar is already upwards of 10 times the mass of our sun .

Generative recommendations (GR), which usually include item tokenizers and generative Large Language Models (LLMs), have demonstrated remarkable success across a wide range of scenarios. The majority of existing research efforts primarily concentrate on developing powerful item tokenizers or advancing LLM decoding strategies to attain superior performance. However, the critical fine-tuning step in GR frameworks, which is essential for adapting LLMs to recommendation data, remains largely unexplored. Current approaches predominantly rely on either the next-token prediction loss of supervised fine-tuning (SFT) or recommendationspecific direct preference optimization (DPO) strategies. Both methods ignore the exploration of possible positive unobserved samples, which is commonly referred to as the exposure bias problem. To mitigate this problem, this paper treats the GR as a multi-step generation task and constructs a GFlowNets-based fine-tuning framework (GFlowGR). The proposed framework integrates collaborative knowledge from traditional recommender systems to create an adaptive trajectory sampler and a comprehensive reward model. Leveraging the diverse generation property of GFlowNets, along with sampling and heuristic weighting techniques, GFlowGR emerges as a promising approach to mitigate the exposure bias problem. Extensive empirical results on two real-world datasets and with two different GR backbones highlight the effectiveness and robustness of GFlowGR.

ALI-Agent operates through two principal stages: Emulation and Refinement. During the Emulation stage, ALI-Agent automates the generation of realistic test scenarios.

Sequential recommendation systems predict the next interaction item based on users' past interactions, aligning recommendations with individual preferences.

Robotic manipulation systems are increasingly deployed across diverse domains. Y et existing multi-modal learning frameworks lack inherent guarantees of geometric consistency, struggling to handle spatial transformations such as rotations and translations. While recent works attempt to introduce equivariance through bespoke architectural modifications, these methods suffer from high implementation complexity, computational cost, and poor portability. Inspired by human cognitive processes in spatial reasoning, we propose Eq.Bot, a universal canonicalization framework grounded in SE(2) group eq uivariant theory for robot ic manipulation learning. Our framework transforms observations into a canonical space, applies an existing policy, and maps the resulting actions back to the original space. As a model-agnostic solution, Eq.Bot aims to endow models with spatial equivariance without requiring architectural modifications. Extensive experiments demonstrate the superiority of Eq.Bot under both CNN-based (e.g., CLI-Port) and Transformer-based (e.g., OpenVLA-OFT) architectures over existing methods on various robotic manipulation tasks, where the most significant improvement can reach 50.0%.

We use bold lower-case letters to denote vectors, e.g.,