Moscow hit by largest Ukrainian attack since start of Russia's full-scale war Moscow has come under the largest Ukrainian attack since the start of the full-scale war, with close to 200 drones hitting targets around the Russian capital and setting columns of thick smoke billowing high into the sky. Seventeen people were wounded in the Moscow region, according to local governor Andrei Vorobyov. Almost 1,000 drones and four Ukrainian cruise missiles were intercepted and destroyed across the country in 24 hours, Russia's defence ministry was quoted as saying. An oil depot was struck in the southern Rostov region, where one person was killed. Volodymyr Zelensky said Kyiv had once again hit the Moscow region with long-range sanctions - a euphemism for Ukrainian long-distance strikes on Russia.

This work introduces panoptic captioning, a novel task striving to seek the minimum text equivalent of images, which has broad potential applications. We take the first step towards panoptic captioning by formulating it as a task of generating a comprehensive textual description for an image, which encapsulates all entities, their respective locations and attributes, relationships among entities, as well as global image state. Through an extensive evaluation, our work reveals that state-of-the-art Multi-modal Large Language Models (MLLMs) have limited performance in solving panoptic captioning. To address this, we propose an effective data engine named PancapEngine to produce high-quality data and a novel method named PancapChain to improve panoptic captioning. Specifically, our PancapEngine first detects diverse categories of entities in images by an elaborate detection suite, and then generates required panoptic captions using entity-aware prompts. Additionally, our PancapChain explicitly decouples the challenging panoptic captioning task into multiple stages and generates panoptic captions step by step. More importantly, we contribute a comprehensive metric named PancapScore and a human-curated test set for reliable model evaluation. Experiments show that our PancapChain-13B model can beat state-of-the-art opensource MLLMs like InternVL-2.5-78B and even surpass proprietary models like GPT-4o and Gemini-2.0-Pro,

Xing identifying chronizing illustrated audio et (V2A) al., in the multiple 2024; Figure generation subtle

The recent DeepSeek-R1 release has demonstrated the immense potential of reinforcement learning (RL) in enhancing the general reasoning capabilities of large language models (LLMs). While DeepSeek-R1 and other follow-up work primarily focus on applying RL to competitive coding and math problems, this paper introduces SWE-RL, the first approach to scale RL-based LLM reasoning for real-world software engineering. Leveraging a lightweight rule-based reward (e.g., the similarity score between ground-truth and LLM-generated solutions), SWE-RL enables LLMs to autonomously recover a developer's reasoning processes and solutions by learning from extensive open-source software evolution data--the record of entire software development cycles, including code snapshots, code changes, and events such as issues and pull requests. Trained on top of Llama 3, our resulting reasoning model, Llama3-SWE-RL-70B, achieves a 41.0% solve rate on SWEbench Verified--a human-verified collection of real-world GitHub issues. To our knowledge, this is the best performance reported for medium-sized (<100B) LLMs to date, even comparable to leading proprietary LLMs like GPT-4o. Surprisingly, despite performing RL solely on software evolution data, Llama3-SWE-RL has even emerged with generalized reasoning skills. For example, it shows improved results on five out-of-domain tasks, namely, function coding, library use, code reasoning, mathematics, and general language understanding, whereas a supervisedfinetuning baseline even leads to performance degradation on average. Overall, SWE-RL opens up a new direction to improve the reasoning capabilities of LLMs through reinforcement learning on massive software engineering data.

Model editing enables targeted updates to the knowledge of large language models (LLMs) with minimal retraining. Among existing approaches, locate-then-edit methods constitute a prominent paradigm: they first identify critical layers, then compute residuals at the final critical layer based on the target edit, and finally apply least-squares-based multi-layer updates via residual distribution. While empirically effective, we identify a counterintuitive failure mode: residual distribution, a core mechanism in these methods, introduces weight shift errors that undermine editing precision. Through theoretical and empirical analysis, we show that such errors increase with the distribution distance, batch size, and edit sequence length, ultimately leading to inaccurate or suboptimal edits. To address this, we propose the Boundary Layer UpdatE (BLUE) strategy to enhance locate-then-edit methods. Sequential batch editing experiments on three LLMs and two datasets demonstrate that BLUE not only delivers an average performance improvement of 35.59%, significantly advancing the state of the art in model editing, but also enhances the preservation of LLMs' general capabilities. Our code is available at https://github.com/xpq-tech/BLUE.

Russia’s defense ministry said 555 drones were shot down across the country. Sobyanin said 180 were shot down around Moscow alone.

Measuring progress is fundamental to the advancement of any scientific field. As benchmarks play an increasingly central role, they also become more susceptible to distortion. Chatbot Arena has emerged as the go-to leaderboard for ranking the most capable AI systems. Yet, in this work we identify systematic issues that have skewed the competitive landscape. Specifically, undisclosed private testing practices benefit a handful of providers who are able to test multiple variants before public release and selectively retract scores.

For an LLM to correctly respond to an instruction it must understand both the semantics and the domain (i.e., subject area) of a given task-instruction pair. However, syntax can also convey implicit information. Recent work shows that syntactic templates--frequent sequences of Part-of-Speech (PoS) tags--are prevalent in training data and often appear in model outputs. In this work we characterize syntactic templates, domain, and semantics in task-instruction pairs. We identify cases of spurious correlations between syntax and domain, where models learn to associate a domain with syntax during training; this can sometimes override prompt semantics.

With the growing demand for deploying large language models (LLMs) across diverse applications, improving their inference efficiency is crucial for sustainable and democratized access. However, retraining LLMs to meet new user-specific requirements is prohibitively expensive and environmentally unsustainable. In this work, we propose a practical and scalable alternative: composing efficient hybrid language models from existing pre-trained models. Our approach, Zebra-Llama, introduces a family of 1B, 3B, and 8B hybrid models by combining State Space Models (SSMs) and Multi-head Latent Attention (MLA) layers, using a refined initialization and post-training pipeline to efficiently transfer knowledge from pre-trained Transformers. Zebra-Llama achieves Transformer-level accuracy with near-SSM efficiency using only 7-11B training tokens (compared to trillions of tokens required for pre-training) and an 8B teacher. Moreover, Zebra-Llama dramatically reduces KV cache size--down to 3.9%, 2%, and 2.73% of the original for the 1B, 3B, and 8B variants, respectively--while preserving 100%, 100%, and >97% of average zero-shot performance on LMHarness tasks. Compared to models like MambaInLLaMA, X-EcoMLA, Minitron, and Llamba, Zebra-Llama consistently delivers competitive or superior accuracy while using significantly fewer tokens, smaller teachers, and vastly reduced KV cache memory.

Reasoning-enhanced large language models (RLLMs), whether explicitly trained for reasoning or prompted via chain-of-thought (CoT), have achieved state-ofthe-art performance on many complex reasoning tasks. However, we uncover a surprising and previously overlooked phenomenon: explicit CoT reasoning can significantly degrade instruction-following accuracy. Evaluating 20+ models on two benchmarks: IFEval (with simple, rule-verifiable constraints) and ComplexBench (with complex, compositional constraints), we consistently observe performance drops when CoT prompting is applied. Through large-scale case studies and an attention-based analysis, we identify common patterns where reasoning either helps (e.g., with formatting or lexical precision) or hurts (e.g., by neglecting simple constraints or introducing unnecessary content). We propose a metric, constraint attention, to quantify model focus during generation and show that CoT reasoning often diverts attention away from instruction-relevant tokens. To mitigate these effects, we introduce and evaluate four strategies: in-context learning, selfreflection, self-selective reasoning, and classifier-selective reasoning. Our results demonstrate that selective reasoning strategies, particularly classifier-selective reasoning, can substantially recover lost performance. To our knowledge, this is the first work to systematically expose reasoning-induced failures in instructionfollowing and offer practical mitigation strategies.