In this paper, we introduce EasyEdit2, a framework designed to enable plug-and-play adjustability for controlling Large Language Model (LLM) behaviors. EasyEdit2 supports a wide range of test-time interventions, including safety, sentiment, personality, reasoning patterns, factuality, and language features. Unlike its predecessor, EasyEdit2 features a new architecture specifically designed for seamless model steering. It comprises key modules such as the steering vector generator and the steering vector applier, which enable automatic generation and application of steering vectors to influence the model's behavior without modifying its parameters. One of the main advantages of EasyEdit2 is its ease of use-users do not need extensive technical knowledge. With just a single example, they can effectively guide and adjust the model's responses, making precise control both accessible and efficient. Empirically, we report model steering performance across different LLMs, demonstrating the effectiveness of these techniques. We have released the source code on GitHub at https://github.com/zjunlp/EasyEdit along with a demonstration notebook. In addition, we provide a demo video at https://www.youtube.com/watch?v=AkfoiPfp5rQ for a quick introduction.

Large language models (LLMs) have achieved remarkable multi-step reasoning capabilities across various domains. However, LLMs still face distinct challenges in complex logical reasoning, as (1) proof-finding requires systematic exploration and the maintenance of logical coherence and (2) searching the right combination of premises at each reasoning step is inherently challenging in tasks with large premise space. To address this, we propose LogicTree, an inference-time modular framework employing algorithm-guided search to automate structured proof exploration and ensure logical coherence. Advancing beyond tree-of-thought (ToT), we incorporate caching mechanism into LogicTree to enable effective utilization of historical knowledge, preventing reasoning stagnation and minimizing redundancy. Furthermore, we address the combinatorial complexity of premise search by decomposing it into a linear process. The refined premise selection restricts subsequent inference to at most one derivation per step, enhancing reasoning granularity and enforcing strict step-by-step reasoning. Additionally, we introduce two LLM-free heuristics for premise prioritization, enabling strategic proof search. Experimental results on five datasets demonstrate that LogicTree optimally scales inference-time computation to achieve higher proof accuracy, surpassing chain-of-thought (CoT) and ToT with average gains of 23.6% and 12.5%, respectively, on GPT-4o. Moreover, within LogicTree, GPT-4o outperforms o3-mini by 7.6% on average.

This study explored how large language models (LLMs) perform in two areas related to art: writing critiques of artworks and reasoning about mental states (Theory of Mind, or ToM) in art-related situations. For the critique generation part, we built a system that combines Noel Carroll's evaluative framework with a broad selection of art criticism theories. The model was prompted to first write a full-length critique and then shorter, more coherent versions using a step-by-step prompting process. These AI-generated critiques were then compared with those written by human experts in a Turing test-style evaluation. In many cases, human subjects had difficulty telling which was which, and the results suggest that LLMs can produce critiques that are not only plausible in style but also rich in interpretation, as long as they are carefully guided. In the second part, we introduced new simple ToM tasks based on situations involving interpretation, emotion, and moral tension, which can appear in the context of art. These go beyond standard false-belief tests and allow for more complex, socially embedded forms of reasoning. We tested 41 recent LLMs and found that their performance varied across tasks and models. In particular, tasks that involved affective or ambiguous situations tended to reveal clearer differences. Taken together, these results help clarify how LLMs respond to complex interpretative challenges, revealing both their cognitive limitations and potential. While our findings do not directly contradict the so-called Generative AI Paradox--the idea that LLMs can produce expert-like output without genuine understanding--they suggest that, depending on how LLMs are instructed, such as through carefully designed prompts, these models may begin to show behaviors that resemble understanding more closely than we might assume.

Earth Observation (EO) provides critical planetary data for environmental monitoring, disaster management, climate science, and other scientific domains. Here we ask: Are AI systems ready for reliable Earth Observation? We introduce \datasetnamenospace, a benchmark of 140 yes/no questions from NASA Earth Observatory articles across 13 topics and 17 satellite sensors. Using Google Earth Engine API as a tool, LLM agents can only achieve an accuracy of 33% because the code fails to run over 58% of the time. We improve the failure rate for open models by fine-tuning synthetic data, allowing much smaller models (Llama-3.1-8B) to achieve comparable accuracy to much larger ones (e.g., DeepSeek-R1). Taken together, our findings identify significant challenges to be solved before AI agents can automate earth observation, and suggest paths forward. The project page is available at https://iandrover.github.io/UnivEarth.

Recent studies have explored integrating large language models (LLMs) into recommendation systems but face several challenges, including training-induced bias and bottlenecks from serialized architecture. To effectively address these issues, we propose a Query-toRecommendation, a parallel recommendation framework that decouples LLMs from candidate pre-selection and instead enables direct retrieval over the entire item pool. Our framework connects LLMs and recommendation models in a parallel manner, allowing each component to independently utilize its strengths without interfering with the other. In this framework, LLMs are utilized to generate feature-enriched item descriptions and personalized user queries, allowing for capturing diverse preferences and enabling rich semantic matching in a zero-shot manner. To effectively combine the complementary strengths of LLM and collaborative signals, we introduce an adaptive reranking strategy. Extensive experiments demonstrate an improvement in performance up to 57%, while also improving the novelty and diversity of recommendations.

Imagine placing your smartphone on a table in a noisy restaurant and clearly capturing the voices of friends seated around you, or recording a lecturer's voice with clarity in a reverberant auditorium. We introduce SonicSieve, the first intelligent directional speech extraction system for smartphones using a bio-inspired acoustic microstructure. Our passive design embeds directional cues onto incoming speech without any additional electronics. It attaches to the in-line mic of low-cost wired earphones which can be attached to smartphones. We present an end-to-end neural network that processes the raw audio mixtures in real-time on mobile devices. Our results show that SonicSieve achieves a signal quality improvement of 5.0 dB when focusing on a 30° angular region. Additionally, the performance of our system based on only two microphones exceeds that of conventional 5-microphone arrays.

This study addresses the problem of hallucinated span detection in the outputs of large language models. It has received less attention than output-level hallucination detection despite its practical importance. Prior work has shown that attentions often exhibit irregular patterns when hallucinations occur. Motivated by these findings, we extract features from the attention matrix that provide complementary views capturing (a) whether certain tokens are influential or ignored, (b) whether attention is biased toward specific subsets, and (c) whether a token is generated referring to a narrow or broad context, in the generation. These features are input to a Transformer-based classifier to conduct sequential labelling to identify hallucinated spans. Experimental results indicate that the proposed method outperforms strong baselines on hallucinated span detection with longer input contexts, such as data-to-text and summarisation tasks.

Traffic crash detection in long-form surveillance videos is essential for improving emergency response and infrastructure planning, yet remains difficult due to the brief and infrequent nature of crash events. We present \textbf{HybridMamba}, a novel architecture integrating visual transformers with state-space temporal modeling to achieve high-precision crash time localization. Our approach introduces multi-level token compression and hierarchical temporal processing to maintain computational efficiency without sacrificing temporal resolution. Evaluated on a large-scale dataset from the Iowa Department of Transportation, HybridMamba achieves a mean absolute error of \textbf{1.50 seconds} for 2-minute videos ($p<0.01$ compared to baselines), with \textbf{65.2%} of predictions falling within one second of the ground truth. It outperforms recent video-language models (e.g., TimeChat, VideoLLaMA-2) by up to 3.95 seconds while using significantly fewer parameters (3B vs. 13--72B). Our results demonstrate effective temporal localization across various video durations (2--40 minutes) and diverse environmental conditions, highlighting HybridMamba's potential for fine-grained temporal localization in traffic surveillance while identifying challenges that remain for extended deployment.

DeeperDive, a new tool that converses with readers, is an effort to beat the AI industry at its own game. The publishing company behind USA Today and 220 other publications is today rolling out a chatbot -like tool called DeeperDive that can converse with readers, summarize insights from its journalism, and suggest new content from across its sites. "Visitors now have a trusted AI answer engine on our platform for anything they want to engage with, anything they want to ask," Mike Reed, CEO of Gannett and the USA Today Network, said at the WIRED AI Power Summit in New York, an event that brought together voices from the tech industry, politics, and the world of media. "and it is performing really great." Most publishers have a fraught relationship with AI, as the chatbots that trained on their content are now summarizing it and eating the traffic that search engines used to send them.

ChatGPT passed the Turing Test. The AI fooled 73% of people into thinking it was human, raising new questions about machine intelligence. As artificial intelligence gets better and better, people face machines that look--and act--surprisingly human. Breakthroughs, discoveries, and DIY tips sent every weekday. It seems that every day brings a new headline about the burgeoning capabilities of large language models (LLMs) like ChatGPT and Google's Gemini--headlines that are either exciting or increasingly apocalyptic, depending on one's point of view. One particularly striking story arrived earlier this year: a paper that described how an LLM had passed the Turing Test, an experiment devised in the 1950s by computer science pioneer Alan Turing to determine whether machine intelligence could be distinguished from that of a human. The LLM in question was ChatGPT 4.5, and the paper found that it had been strikingly successful in fooling people into thinking it was human: In an experiment where participants were asked to choose whether the chatbot or an actual human was the real person, nearly three of the four chose the former.