LongAttnComp: Cross-Family Context Compression for Long-Context Reasoning

As real-world applications increasingly require processing inputs of 100k+ tokens, the gap between context length and inference efficiency has become a critical bottleneck. Context compression offers a way to reduce prefill costs while preserving task accuracy. However, existing training-free attention-based methods leave substantial gaps in demanding long-context tasks such as code reasoning. We present LongAttnComp, a long-context adaptation of AttnComp that fine-tunes a lightweight cross-attention scoring layer and introduces tokenlevel chunking, a token-budget top-p algorithm, positional reordering, and a formatagnostic query parser. We further design a two-stage fine-tuning recipe for the compressor: Stage 1 builds a general retrieval foundation from NIAH-style data, and Stage 2 extends it with multi-hop and reasoning data for broader long-context task coverage. On InfiniteBench Code-Debug, LongAttnComp matches or exceeds full-context accuracy, substantially outperforms training-free baselines, and transfers across four target models from three families. On LongBench v2, the two-stage recipe largely closes the Stage 1 gap on multi-document reasoning while preserving Code-Debug performance.

SkillSmith: Co-Evolving Skills and Tools for Self-Improving Agent Systems

Recent self-evolving agents have shown that skills can be discovered, refined, and accumulated through execution. However, existing skill-evolution frameworks typically assume a fixed tool layer and evaluate each skill independently, limiting their ability to repair tool-level failures or reason about interactions among skills. We propose SkillSmith, a synergy-aware skill-tool co-evolution framework. SkillSmith introduces a unified proposal space in which reflection produces atomic bundles that jointly modify skills and tools, allowing tools to be wrapped, edited, composed, split, or retired when skill evolution identifies a reusable capability gap. To guide this joint search, SkillSmith maintains an ecological utility model inspired by Lotka-Volterra dynamics, where an interaction matrix estimated from execution traces captures pairwise complementarity and conflict among skills and provides pressure signals for retrieval, mutation prioritization, and retirement. Furthermore, SkillSmith records anti-patterns, including failure signatures, causal attributions, and remedies, to accelerate diagnosis and veto proposals that repeat known mistakes. Experiments on three benchmarks, including WildClawBench, and five Qwen3.5 model scales show that SkillSmith consistently outperforms strong baselines, with gains that amplify as task complexity and multi-skill co-activation increase.

Understanding and Mitigating Premature Confidence for Better LLM Reasoning

Long chains of thought (CoT) from current language models frequently contain logical gaps and unjustified leaps, limiting the gains from additional test-time compute. Improving reasoning quality directly would require process reward models, but the step-level annotations needed to train them are expensive and scarce. We find such a signal in how the model's confidence evolves during reasoning: premature confidence, the tendency to commit to an answer early and use the remaining tokens to rationalize it, strongly predicts flawed reasoning across tasks and model scales. We exploit this in progressive confidence shaping, a reinforcement learning objective that trains models to update their confidence as they reason rather than commit early -- rewarding gradual confidence growth and penalizing early commitment, with no external labels or reward models. The method improves accuracy and reasoning quality from 1.5B to 8B parameters across arithmetic (Countdown), math (DAPO, AIME), and science (ScienceQA): on Countdown, accuracy improves 3.2x (+42.0pp) and flawed reasoning drops 48pp; on AIME, Pass@64 improves 6.6pp. Consistent with this mechanism, the method also improves faithfulness: on a safety benchmark, our models more transparently surface misleading content in their reasoning traces rather than concealing it. Controlled experiments reveal that the problem and its remedy scale together: premature confidence grows with model size and task difficulty, and so do the gains from addressing it.

StepAudio 2.5 Technical Report

Unified audio-language modeling has emerged as a prominent trend in modern speech systems, promising to bring the reasoning capabilities of large language models to auditory tasks. However, existing unified foundations often struggle to match the depth of specialized systems across automatic speech recognition (ASR), text-to-speech synthesis (TTS), and realtime spoken interaction. Bridging this gap remains an open challenge. This report presents StepAudio 2.5, a unified audio-language foundation model that matches or exceeds specialized systems across all three capabilities. Rather than treating these tasks as architecturally distinct, we operate on the premise that once text and audio share a multimodal representational space, task specialization becomes a matter of operational regimes: data construction, optimization targets, and decoding constraints. Guided by this insight, we advance the post-training paradigm from standard supervised learning to task-tailored Reinforcement Learning from Human Feedback (RLHF), using it as the primary mechanism to define complex optimization targets. We leverage this RLHF-centric alignment, alongside specialized decoding, to shape a shared backbone into three distinct operational modes. Concretely, the ASR branch advances transcription efficiency via verifiable multi-token decoding; the TTS branch achieves controllable, expressive synthesis through preference-based RLHF and context-rich supervision; and the Realtime branch realizes low-latency, persona-consistent dialogue via generative reward modeling within an RLHF framework. On standard benchmarks, StepAudio 2.5 achieves state-of-the-art results across ASR, TTS, and Realtime, demonstrating that a singular audio-language foundation can successfully internalize the distinct deployment objectives of speech understanding, generation, and live interaction.

Interactive State Space Model with Cross-Modal Local Scanning for Depth Super-Resolution

Guided depth super-resolution (GDSR) reconstructs HR depth maps from LR inputs with HR RGB guidance. Existing methods either model each modality independently or rely on computationally expensive attention mechanisms with quadratic complexity, hindering the establishment of efficient and semantically interactive joint representations. In this paper, we observe that feature maps from different modalities exhibit semantic-level correlations during feature extraction. This motivates us to develop a more flexible approach enabling dense, semantically-aware deep interactions between modalities. To this end, we propose a novel GDSR framework centered around the Interactive State Space Model. Specifically, we design a cross-modal local scanning mechanism that enables fine-grained semantic interactions between RGB and depth features. Leveraging the Mamba architecture, our framework achieves global modeling with linear complexity. Furthermore, a cross-modal matching transform module is introduced to enhance interactive modeling quality by utilizing representative features from both modalities. Extensive experiments demonstrate competitive performance against state-of-the-art methods.

6thGrid-Net: Unified Remote Sensing Image Dehazing Based on Color Restoration and Edge-Preserving

Remote sensing images are frequently degraded by adverse weather conditions, particularly clouds and haze, which severely impair downstream applications. Existing restoration methods typically rely on computationally heavy architectures or sequential pipelines (e.g., detail enhancement followed by color rendition) that suffer from mutual interference and artifact accumulation. Furthermore, recent unified grid-based approaches utilize fixed, isotropic interpolation kernels, neglecting the intrinsic low-dimensional manifold of natural images and inevitably causing edge blur. To address these limitations, we propose 6th Grid-Net, a highly efficient and unified remote sensing image restoration framework tailored for resource-constrained edge devices. Specifically, we construct a novel six-dimensional fusion tensor that seamlessly integrates the color rendition capabilities of 3D LUTs with the spatial-luminance detail preservation of bilateral grids. To overcome the drawbacks of standard trilinear interpolation, we introduce a manifold-adaptive high-dimensional sampling mechanism. This mechanism dynamically adjusts the interpolation kernel based on local edge orientation, texture strength, and color similarity, enabling simultaneous global color stylization and local edge refinement in a single forward pass. Additionally, an edge-aware grid smoothing constraint and dynamic quantization are incorporated to suppress ghosting artifacts and significantly compress the model size. Extensive experiments on multiple benchmark datasets demonstrate that 6th Grid-Net achieves state-of-the-art restoration quality across various degradation scenarios.

ChangeQuery: Advancing Remote Sensing Change Analysis for Natural and Human-Induced Disasters from Visual Detection to Semantic Understanding

Rapid situational awareness is critical in post-disaster response. While remote sensing damage assessment is evolving from pixel-level change detection to high-level semantic analysis, existing vision-language methodologies still struggle to provide actionable intelligence for complex strategic queries. They remain severely constrained by unimodal optical dependence, a prevailing bias towards natural disasters, and a fundamental lack of grounded interactivity. To address these limitations, we present ChangeQuery, a unified multimodal framework designed for comprehensive, all-weather disaster situation awareness. To overcome modality constraints and scenario biases, we construct the Disaster-Induced Change Query (DICQ) dataset, a large-scale benchmark coupling pre-event optical semantics with post-event SAR structural features across a balanced distribution of natural catastrophes and armed conflicts. Furthermore, to provide the high-quality supervision required for interactive reasoning, we propose a novel Automated Semantic Annotation Pipeline. Adhering to a ``statistics-first, generation-later'' paradigm, this engine automatically transforms raw segmentation masks into grounded, hierarchical instruction sets, effectively equipping the model with fine-grained spatial and quantitative awareness. Trained on this structured data, the ChangeQuery architecture operates as an interactive disaster analyst. It supports multi-task reasoning driven by diverse user queries, delivering precise damage quantification, region-specific descriptions, and holistic post-disaster summaries. Extensive experiments demonstrate that ChangeQuery establishes a new state-of-the-art, providing a robust and interpretable solution for complex disaster monitoring. The code is available at \href{https://sundongwei.github.io/changequery/}{https://sundongwei.github.io/changequery/}.

Can Explicit Physical Feasibility Benefit VLA Learning? An Empirical Study

Vision-Language-Action (VLA) models map multimodal inputs directly to robot actions and are typically trained through large-scale imitation learning. While this paradigm has shown strong performance, prevailing VLA training procedures do not explicitly supervise hard physical constraints such as obstacle avoidance or kinematic feasibility. As a result, the geometric structure underlying physically feasible behavior must be inferred only implicitly from demonstrations. In this paper, we study whether introducing explicit feasibility supervision can provide effective structured guidance for VLA policies. We formulate a simple geometry-grounded feasibility objective and integrate it into the training stage of a diffusion-based VLA policy. To evaluate this idea systematically, we use obstacle-aware manipulation as a controlled probe of geometry-dependent physical feasibility. Empirical results show that augmenting VLA training with feasibility supervision improves both physical reliability and overall task performance, while also enhancing learning efficiency in the low-data regime. These findings indicate that explicit feasibility signals can effectively complement imitation-based VLA learning, highlighting their potential for developing more reliable VLA policies.

UHD-GPGNet: UHD Video Denoising via Gaussian-Process-Guided Local Spatio-Temporal Modeling

Ultra-high-definition (UHD) video denoising requires simultaneously suppressing complex spatio-temporal degradations, preserving fine textures and chromatic stability, and maintaining efficient full-resolution 4K deployment. In this paper, we propose UHD-GPGNet, a Gaussian-process-guided local spatio-temporal denoising framework that addresses these requirements jointly. Rather than relying on implicit feature learning alone, the method estimates sparse GP posterior statistics over compact spatio-temporal descriptors to explicitly characterize local degradation response and uncertainty, which then guide adaptive temporal-detail fusion. A structure-color collaborative reconstruction head decouples luminance, chroma, and high-frequency correction, while a heteroscedastic objective and overlap-tiled inference further stabilize optimization and enable memory-bounded 4K deployment. Experiments on UVG and RealisVideo-4K show that UHD-GPGNet achieves competitive restoration fidelity with substantially fewer parameters than existing methods, enables real-time full-resolution 4K inference with significant speedup over the closest quality competitor, and maintains robust performance across a multi-level mixed-degradation schedule.A real-world study on phone-captured 4K video further confirms that the model, trained entirely on synthetic degradation, generalizes to unseen real sensor noise and improves downstream object detection under challenging conditions.

UHD Low-Light Image Enhancement via Real-Time Enhancement Methods with Clifford Information Fusion

Considering efficiency, ultra-high-definition (UHD) low-light image restoration is extremely challenging. Existing methods based on Transformer architectures or high-dimensional complex convolutional neural networks often suffer from the "memory wall" bottleneck, failing to achieve millisecond-level inference on edge devices. To address this issue, we propose a novel real-time UHD low-light enhancement network based on geometric feature fusion using Clifford algebra in 2D Euclidean space. First, we construct a four-layer feature pyramid with gradually increasing resolution, which decomposes input images into low-frequency and high-frequency structural components via a Gaussian blur kernel, and adopts a lightweight U-Net based on depthwise separable convolution for dual-branch feature extraction. Second, to resolve structural information loss and artifacts from traditional high-low frequency feature fusion, we introduce spatially aware Clifford algebra, which maps feature tensors to a multivector space (scalars, vectors, bivectors) and uses Clifford similarity to aggregate features while suppressing noise and preserving textures. In the reconstruction stage, the network outputs adaptive Gamma and Gain maps, which perform physically constrained non-linear brightness adjustment via Retinex theory. Integrated with FP16 mixed-precision computation and dynamic operator fusion, our method achieves millisecond-level inference for 4K/8K images on a single consumer-grade device, while outperforming state-of-the-art (SOTA) models on several restoration metrics.