In contrast, we propose to inject steering vectors directly into the query and value representation spaces within attention heads. We provide evidence that a greater portion of these spaces exhibit high linear discriminability of concepts -a key property motivating the use of steering vectors-than attention head outputs. We analytically characterize the effect of our method, which we term DISentangled COmmunication (DISCO) Steering, on attention head outputs. Our analysis reveals that DISCO disentangles a strong but underutilized baseline, steering attention head inputs, which implicitly modifies queries and values in a rigid manner. In contrast, DISCO's direct modulation of these components enables more granular control. We find that DISCO achieves superior performance over a number of steering vector baselines across multiple datasets on LLaMA 3.1 8B and Gemma 2 9B, with steering efficacy scoring up to 19.1%higher than the runner-up. Our results support the conclusion that the query and value spaces are powerful building blocks for steering vector methods. Our code is publicly available at https://github.com/MaxTorop/DISCO.

In recent years, neural network-guided heuristic search algorithms, such as MonteCarlo tree search and A search, have achieved significant advancements across diverse practical applications. Due to the challenges stemming from high statespace complexity, sparse training datasets, and incomplete environmental modeling, heuristic estimations manifest uncontrolled inherent biases towards the actual expected evaluations, thereby compromising the decision-making quality of search algorithms. Sampling exploration enhanced A (SeeA) was proposed to improve the efficiency of A search by constructing an dynamic candidate subset through random sampling, from which the expanded node was selected.

Biological circuits have evolved to incorporate multiple modules that perform similar functions. In the fly olfactory circuit, both lateral inhibition (LI) and neuronal spike frequency adaptation (SFA) are thought to enhance pattern separation for odor learning. However, it remains unclear whether these mechanisms play redundant or distinct roles in this process. In this study, we present a computational model of the fly olfactory circuit to investigate odor discrimination under varying noise conditions that simulate complex environments. Our results show that LI primarily enhances odor discrimination in low-and medium-noise scenarios, but this benefit diminishes and may reverse under higher-noise conditions. In contrast, SFA consistently improves discrimination across all noise levels. LI is preferentially engaged in low-and medium-noise environments, whereas SFA dominates in high-noise settings. When combined, these two sparsification mechanisms enable optimal discrimination performance. This work demonstrates that seemingly redundant modules in biological circuits can, in fact, be essential for achieving optimal learning in complex contexts.

Recent advancements have increasingly focused on leveraging large language models (LLMs) to construct autonomous agents for complex problem-solving tasks. However, existing approaches predominantly employ a single-agent framework to generate search branches and estimate rewards during Monte Carlo Tree Search (MCTS) planning. This single-agent paradigm inherently limits exploration capabilities, often resulting in insufficient diversity among generated branches and suboptimal planning performance. To overcome these limitations, we propose SYnergistic Multi-agent Planning with HeterOgeneous laNgauge model assemblY (SYMPHONY 2), a novel multi-agent planning framework that integrates a pool of heterogeneous language model-based agents. By leveraging diverse reasoning patterns across agents, SYMPHONY enhances rollout diversity and facilitates more effective exploration. Empirical results across multiple benchmark tasks show that SYMPHONY achieves strong performance even when instantiated with open-source LLMs deployable on consumer-grade hardware. When enhanced with cloud-based LLMs accessible via API, SYMPHONY demonstrates further improvements, outperforming existing state-of-the-art baselines and underscoring the effectiveness of heterogeneous multi-agent coordination in planning tasks.

To address these challenges, we introduce Refer-Judge, a novel framework that harnesses the reasoning capabilities of Multimodal Large Language Models (MLLMs) to identify and mitigate toxic data. At the core of Refer-Judge is a Jury-andJudge Chain-of-Thought paradigm, inspired by the deliberative process of the judicial system. This framework targets the root causes of annotation noise: jurors collaboratively assess 3DVG samples from diverse perspectives, providing structured, multi-faceted evaluations. Judges then consolidate these insights using a Corroborative Refinement strategy, which adaptively reorganizes information to correct ambiguities arising from biased or incomplete observations. Through this two-stage deliberation, Refer-Judge significantly enhances the reliability of data judgments. Extensive experiments demonstrate that our framework not only achieves human-level discrimination at the scene level but also improves the performance of baseline algorithms via data purification. Code is available at https://github.com/Hermione-HKX/Refer_Judge.

Reinforcement Learning with Verifiable Rewards (RLVR) has recently demonstrated notable success in enhancing the reasoning performance of large language models (LLMs), particularly in mathematics and programming tasks. It is widely believed that, similar to how traditional RL helps agents to explore and learn new strategies, RLVR enables LLMs to continuously self-improve, thus acquiring novel reasoning abilities that exceed the capacity of the corresponding base models. In this study, we take a critical look at the current state of RLVR by systematically probing the reasoning capability boundaries of RLVR-trained LLMs across various model families, RL algorithms, and math/coding/visual reasoning benchmarks, using pass@k at large k values as the evaluation metric. While RLVR improves sampling efficiency towards correct paths, we surprisingly find that current training does not elicit fundamentally new reasoning patterns. We observe that while RLVR-trained models outperform their base models at smaller values of k (e.g., k=1), base models achieve higher pass@k score when k is large. Moreover, we observe that the reasoning capability boundary of LLMs often narrows as RLVR training progresses.

Leveraging recent diffusion models, LiDAR-based large-scale 3D scene generation has achieved great success. While recent voxel-based approaches can generate both geometric structures and semantic labels, existing range-view methods are limited to producing unlabeled LiDAR scenes. Relying on pretrained segmentation models to predict the semantic maps often results in suboptimal cross-modal consistency. To address this limitation while preserving the advantages of range-view representations, such as computational efficiency and simplified network design, we propose SPIRAL, a novel range-view LiDAR diffusion model that simultaneously generates depth, reflectance images, and semantic maps. Furthermore, we introduce novel semantic-aware metrics to evaluate the quality of the generated labeled range-view data. Experiments on the SemanticKITTI and nuScenes datasets demonstrate that SPIRAL achieves state-of-the-art performance with the smallest parameter size, outperforming two-step methods that combine the generative and segmentation models. Additionally, we validate that range images generated by SPIRAL can be effectively used for synthetic data augmentation in the downstream segmentation training, significantly reducing the labeling effort on LiDAR data.

Experiments ved spatioacross multiple datasets show that our approach produces significantly more stable and geometrically consistent results than existing baselines.

When you purchase through links in our articles, we may earn a small commission. Google One charges forever -- Internxt's 10TB lifetime plan is $269.97 Internxt takes your privacy seriously. Files are encrypted on your device before upload, then split into fragments and distributed across secure servers, meaning Internxt itself has zero ability to read your data. It runs on a zero-knowledge model, is fully open source, meets GDPR standards, and has been independently audited.

When you purchase through links in our articles, we may earn a small commission. Lifetime access to Microsoft Office Professional Plus 2019 for Windows is $19.97 (MSRP $229) during Deal Days -- one payment, lifetime access, no subscription required. Paying monthly for Office can feel unnecessary if all you really need are the core apps you use every day. Instead of renting software, you can own it outright with a one-time purchase. During Deal Days, our answer to Prime Day running through June 28, Microsoft Office Professional Plus 2019 for Windows is available for $19.97 (MSRP $229), giving you permanent access to Word, Excel, PowerPoint, Outlook, OneNote, Publisher, and Access with no recurring fees.