Link prediction also has significant implications from a fundamental point of view, as it allows for the identification of the elementary mechanisms behind the creation and decay of links in time-evolving networks (Leskovec et al., 2008). For example, triadic closure, at the core of standard methods of link prediction is considered as one of the driving forces for the creation of links in social networks (Kossinets and Watts, 2006). In general, link prediction consists in inferring the existence of a set of links from the observed structure of a network. The edges predicted may correspond to links that are bound to appear in the future, as in the seminal formulation by Liben-Nowell and Kleinberg (2007). They may also be existing links that have not been detected during the data collection process, in which case it is sometimes referred to as the missing link problem. In both cases, it can be described as a binary classification issue, where it is decided if a pair of nodes is connected or not. The features used are often based on the structural properties of the network of known interactions, either at a local scale (e.g. the number of common neighbors) or at a global scale (e.g.

Current approaches to sales conversation analysis and conversion prediction typically rely on Large Language Models (LLMs) combined with basic retrieval augmented generation (RAG). These systems, while capable of answering questions, fail to accurately predict conversion probability or provide strategic guidance in real time. In this paper, we present SalesRLAgent, a novel framework leveraging specialized reinforcement learning to predict conversion probability throughout sales conversations. Unlike systems from Kapa.ai, Mendable, Inkeep, and others that primarily use off-the-shelf LLMs for content generation, our approach treats conversion prediction as a sequential decision problem, training on synthetic data generated using GPT-4O to develop a specialized probability estimation model. Our system incorporates Azure OpenAI embeddings (3072 dimensions), turn-by-turn state tracking, and meta-learning capabilities to understand its own knowledge boundaries. Evaluations demonstrate that SalesRLAgent achieves 96.7% accuracy in conversion prediction, outperforming LLM-only approaches by 34.7% while offering significantly faster inference (85ms vs 3450ms for GPT-4). Furthermore, integration with existing sales platforms shows a 43.2% increase in conversion rates when representatives utilize our system's real-time guidance. SalesRLAgent represents a fundamental shift from content generation to strategic sales intelligence, providing moment-by-moment conversion probability estimation with actionable insights for sales professionals.

As large language models (LLMs) tackle increasingly complex tasks and longer documents, their computational and memory costs during inference become a major bottleneck. To address this, we propose PromptDistill, a novel, training-free method that improves inference efficiency while preserving generation quality. PromptDistill identifies and retains the most informative tokens by leveraging attention interactions in early layers, preserving their hidden states while reducing the computational burden in later layers. This allows the model to focus on essential contextual information without fully processing all tokens. Unlike previous methods such as H2O and SnapKV, which perform compression only after processing the entire input, or GemFilter, which selects a fixed portion of the initial prompt without considering contextual dependencies, PromptDistill dynamically allocates computational resources to the most relevant tokens while maintaining a global awareness of the input. Experiments using our method and baseline approaches with base models such as LLaMA 3.1 8B Instruct, Phi 3.5 Mini Instruct, and Qwen2 7B Instruct on benchmarks including LongBench, InfBench, and Needle in a Haystack demonstrate that PromptDistill significantly improves efficiency while having minimal impact on output quality compared to the original models. With a single-stage selection strategy, PromptDistill effectively balances performance and efficiency, outperforming prior methods like GemFilter, H2O, and SnapKV due to its superior ability to retain essential information. Specifically, compared to GemFilter, PromptDistill achieves an overall $1\%$ to $5\%$ performance improvement while also offering better time efficiency. Additionally, we explore multi-stage selection, which further improves efficiency while maintaining strong generation performance.

--In this paper, we study the underwater acoustic localization in the presence of environmental mismatch. Especially, we exploit a pre-trained neural network for the acoustic wave propagation in a gradient-based optimization framework to estimate the source location. T o alleviate the effect of mismatch between the training data and the test data, we simultaneously optimize over the network weights at the inference time, and provide conditions under which this method is effective. Moreover, we introduce a physics-inspired modularity in the forward model that enables us to learn the path lengths of the multipath structure in an end-to-end training manner without access to the specific path labels. We investigate the validity of the assumptions in a simple yet illustrative environment model.

Large language Models (LLMs) have demonstrated remarkable skills across various domains. Understanding the mechanisms behind their abilities and implementing controls over them is becoming increasingly important for developing better models. In this paper, we focus on skill unlearning in LLMs, specifically unlearning a particular skill while retaining their overall capabilities. We introduce two lightweight, training-free machine skill unlearning techniques for LLMs. First, we observe that the pre-activation distribution of neurons in each Feed-Forward Layer (FFL) differs when the model demonstrates different skills. Additionally, we find that queries triggering the same skill cluster within the FFL key space and can be separated from other queries using a hypercube. Based on these observations, we propose two lightweight, training-free skill unlearning methods via \textit{intervention} and \textit{abstention} respectively: \texttt{Neuron Adjust} and \texttt{Key Space Detection}. We evaluate our methods on unlearning math-solving, Python-coding, and comprehension skills across seven different languages. The results demonstrate their strong unlearning capabilities for the designated skills. Specifically, \texttt{Key Space Detection} achieves over 80\% relative performance drop on the forgetting skill and less than 10\% relative performance drop on other skills and the model's general knowledge (MMLU) for most unlearning tasks. Our code is available at https://github.com/Trustworthy-ML-Lab/effective_skill_unlearning

Recently, 3D reconstruction and generation have demonstrated impressive novel view synthesis results, achieving high fidelity and efficiency. However, a notable conditioning gap can be observed between these two fields, e.g., scalable 3D scene reconstruction often requires densely captured views, whereas 3D generation typically relies on a single or no input view, which significantly limits their applications. W e found that the source of this phenomenon lies in the misalignment between 3D constraints and generative priors. T o address this problem, we propose a reconstruction-driven video diffusion model that learns to condition video frames on artifact-prone RGB-D renderings. Moreover, we propose a cyclical fusion pipeline that iteratively adds restoration frames from the generative model to the training set, enabling progressive expansion and addressing the viewpoint saturation limitations seen in previous reconstruction and generation pipelines. Our evaluation, including view synthesis from sparse view and masked input, validates the effectiveness of our approach.

Multilingual Natural Language Generation (NLG) is challenging due to the lack of training data for low-resource languages. However, some low-resource languages have up to tens of millions of speakers globally, making it important to improve NLG tools for them. Table-to-Text NLG is an excellent measure of models' reasoning abilities but is very challenging in the multilingual setting. System outputs are often not attributable, or faithful, to the data in the source table. Intermediate planning techniques like Question-Answer (QA) blueprints have been shown to improve attributability on summarisation tasks. This work explores whether QA blueprints make multilingual Table-to-Text outputs more attributable to the input tables. This paper extends the challenging multilingual Table-to-Text dataset, TaTA, which includes African languages, with QA blueprints. Sequence-to-sequence language models are then finetuned on this dataset, with and without blueprints. Results show that QA blueprints improve performance for models finetuned and evaluated only on English examples, but do not demonstrate gains in the multilingual setting. This is due to inaccuracies in machine translating the blueprints from English into target languages when generating the training data, and models failing to rely closely on the blueprints they generate. An in-depth analysis is conducted on why this is challenging.

I have spent years investigating serious criminals. From human traffickers and gunrunners to contract killers and cocaine smugglers. One thing I never thought I'd end up investigating was whisky. BBC Producer Liam McDougall told me of a source he had – a whistleblower – who said that organised crime had infiltrated the whisky industry, that he had compiled a hitlist of suspect whisky investment companies, and would we be interested in looking into it? One of those on the list was a company called Cask Whisky Ltd.

Elon Musk's artificial intelligence firm xAI has acquired his social media platform X in an all-stock transaction that values the company at 33 billion, including 12 billion worth of debt, the centibillionaire announced Friday. The sale comes just weeks after Musk reportedly raised an additional roughly 1 billion in debt financing for X that valued the company at 44 billion--the same price Musk paid for it three years ago. "xAI and X's futures are intertwined," Musk wrote in an X post. "Today, we officially take the step to combine the data, models, compute, distribution and talent. This combination will unlock immense potential by blending xAI's advanced AI capability and expertise with X's massive reach."

Elon Musk's AI company, xAI, has purchased X, according to a post shared by Musk. Besides their similar names and owner, the companies are already connected through xAI's chatbot Grok, which is integrated into X. X was acquired by xAI through an all-stock transaction. "The combination values xAI at 80 billion and X at 33 billion ( 45B less 12B debt)," Musk writes. "xAI and X's futures are intertwined."