arXiv subjects
Publications and source records attributed to Jian Zhang.
In this paper, we construct Gelfand--Tsetlin bases for representations of $\mathrm U_q(\mathfrak{gl}_n)$ at roots of unity. As an application, we obtain explicit bases for certain baby Verma modules of $\mathrm U_q(\mathfrak{gl}_3)$ and determine their composition series.
Posterior-collapse diagnostics can show that a VAE uses its latent representation, but they do not determine whether a specified information view crosses a representation/readout interface fixed before training. Reconstruction-Student-Teacher (RST) makes this stronger requirement explicit: Reconstruction supplies the VAE objective, the Student is a fixed witness, and the Teacher is a frozen information specification. We derive a teacher-relative certificate showing that a positive margin guarantees transmission of the declared information through the prescribed interface, while every input-independent representation lies at or below the boundary. A centered regular-simplex witness turns this certificate into an explicit construction: a minimum-dimensional closed-form teacher code, its complete affine solution fiber, witness-visible and witness-null routing, a margin-energy path, function-space departure from the centered input-independent point, preservation cylinders, and orthogonal multi-view composition. Experiments on five datasets test boundary crossing, stronger KL pressure, teacher counterfactuals, null routing, escape, preservation, cross-seed reuse, and cross-architecture reuse. On CIFAR-100, auxiliary learned readers remain natively decodable but fail under no-refit transfer, whereas the same fixed RST witness directly reads independently trained ConvVAE and ResVAE encoders. Affine adapters recover transferred auxiliary readers, localizing much of the failure to interface-coordinate mismatch rather than absence of information. These results support prescribed alignment as distinct from ordinary decodability.
Let $[0,1]_*$ be the unit interval $[0,1]$ equipped with a left-continuous t-norm $*$. We prove that $[0,1]_*\text{-}\mathbf{Set}$ is cartesian closed if and only if $*$ is the minimum t-norm. This extends the classification for continuous t-norms established in the first part of this work to the whole left-continuous setting.
While 3D Gaussian Splatting (3DGS) has revolutionized 3D reconstruction and novel-view synthesis, scenarios with limited input views often lead to poor reconstruction quality and artifacts in rendered novel views. Recent efforts attempt to utilize powerful diffusion priors, yet they typically process rendered and reference views concatenated along an additional dimension in a single network. These methods overlook an inherent nature that different views should maintain appearance similarity but differ in structure due to view shifts, leading to blur caused by conflicts between the two properties. In this paper, we propose DualDiff, a novel pipeline that leverages dual diffusion priors with a Structure-Appearance Attention (SAA) module to introduce reference guidance for refining low-quality novel views rendered from flawed 3D representations. Specifically, we retain one diffusion branch to focus on extracting structural information from the low-quality novel views, while introducing another branch to ensure appearance consistency with reference views. Furthermore, we present a 3D reconstruction framework named DualDiff3D, which integrates a reliability-enhanced Render-Refine-Optimize (RRO) loop to progressively and robustly incorporate the refined novel views, yielding more accurate 3DGS. Extensive experiments demonstrate that our approach outperforms state-of-the-art methods even in the inference-only setting, with further performance gains achievable through training. Our code and pre-trained weights are available at https://github.com/Akaneqwq/DualDiff3D.
Blind face restoration from low-quality images is a challenging task that requires not only high-fidelity image reconstruction, but also preservation of facial identity. Although diffusion models like Stable Diffusion have shown promise in generating high-quality images, their VAE modules are typically trained on broad natural-image data dominated by HQ content; severely degraded LQ inputs therefore yield latents that fall in low-density regions of the diffusion prior, weakening the effectiveness of LQ conditions during the denoising process. Existing approaches often tackle this issue by retraining the VAE encoder, which is computationally expensive and memory intensive. To address this limitation efficiently, we propose LAFR, a codebook-based latent space adapter that aligns LQ latents to the in-distribution region the diffusion prior was trained to denoise, enabling sampling from a better matched latent condition without altering the original VAE. To further improve identity and structural consistency relative to OSEDiff-style baselines, we introduce a multilevel restoration loss combining constraints from semantic identity embeddings and facial structural priors. Furthermore, by leveraging the inherent structural regularity of facial images, we show that lightweight fine-tuning of a diffusion prior on just 0.9% of FFHQ can achieve competitive results while reducing training time by 70%. We also give a short analysis of why a codebook correction closes a mode-dependent latent gap that no global normalisation or affine map can. In summary, LAFR is a data and compute efficient one-step face-restoration method that improves perceptual quality, FID, landmark accuracy, and identity/structure consistency over OSEDiff-style baselines, without claiming uniform state of the art; it reaches this operating point while remaining competitive with far more expensive pipelines.
Policy optimization (PO) for Large Language Models faces a stability--exploration trade-off, currently mediated by an action-side Policy-KL regularizer. This puts practitioners in a double bind: keeping Policy-KL constrains response behavior and consumes the action-side exploration budget, while dropping it leaves the optimization without an explicit drift control. We argue for an alternative that breaks the dilemma by moving regularization to the input side. As training progresses, the distribution over training queries induced by the current policy drifts unchecked from its pre-RL reference distribution. Concretely, Environment-Regularized Policy Optimization (ERPO) introduces a Query-KL (QKL) term that bounds this query distribution shift, together with a dataset-static reference-derived per-query weight that biases each per-query update toward queries typical under the reference. The QKL gradient flows strictly through the query likelihood; the response score function used by policy-gradient estimators does not appear in the QKL term, so QKL exerts no direct gradient pressure on the response distribution---exploration is preserved. ERPO plugs into GRPO/PPO/REINFORCE-style pipelines without additional forward passes. On six mathematical reasoning benchmarks, ERPO replaces the standard Policy-KL regularizer while achieving effective control over query distribution drift, delivering stronger accuracy and substantially more stable behavior under high-temperature decoding and long-horizon training. Our source code are available at https://github.com/AlibabaResearch/ERPO
Deploying wireless nodes to maximize coverage area within a given region is an important challenge in wireless sensor networks, UAV path planning, base station placement and other industrial fields. This practical problem can be mathematically equivalent to an optimal circle covering problem. Although theoretical optimal configurations exist for simple cases in mathematics, the NP-hard nature of this problem makes it computationally prohibitive for complex polygons with numerous nodes. Existing approaches are usually designed for regular domains, while those applicable to irregular polygons often suffer from poor initialization, excessive coverage overlap and failure to constrain nodes within the boundary, leading to low coverage efficiency and long runtime. To address these issues, we propose an improved quasi-physical dynamic algorithm (IQPD) for wireless node deployment in arbitrary convex polygons. Our contributions are threefold: (1) proposing a structure-preserving initialization that maps a hexagonal close packing pattern into the target polygon via scaling and affine transformation, ensuring near-optimal initial node distribution; (2) constructing a refined virtual force model by incorporating friction and a radius-expansion optimization mechanism to reduce coverage area overlap; (3) developing a boundary encircling strategy leveraging normal and tangential gradients to reposition nodes deployed outside boundaries after initial optimization. Extensive experimental results demonstrate that our method consistently outperforms other new metaheuristic algorithms across diverse convex polygon shapes, including randomly generated data and real-world scenarios. Our method achieves the highest coverage rate and node utilization rate among all compared algorithms, greatly improving wireless coverage efficiency.
Search Agents face a severe reliability crisis during reinforcement learning (RL) fine-tuning. Heuristic Top-K retrieval often causes critical evidence loss or noise inclusion, while over-confidence induced by progressive RL leads to hallucinated answers and redundant searches. To build highly reliable agents, we introduce Conformal Prediction (CP) and propose Conformalized Agentic Search (CAS). This framework establishes reliability guarantees on both the retrieval and training sides: on the retrieval side, an Adaptive Prediction Set (APS), a specific CP realization, translates statistical coverage into dynamic document truncation to construct prediction sets that are adaptive in size; on the training side, Adaptive Conformal Inference (ACI), a dynamic CP algorithm, dynamically constructs prediction sets with controllable coverage to quantify answer confidence, which is then used to penalize low-confidence trajectories within the Group Relative Policy Optimization (GRPO) objective, ensuring the model learns only from reliable ones. Experiments across single-hop and multi-hop QA datasets demonstrate that our framework significantly improves reasoning accuracy while drastically reducing redundant tool invocations, establishing a highly reliable and efficient agent paradigm. Our code is available at https://github.com/S1llyBird/CAS.
Multi-step causal reasoning requires chaining inferences where each step constrains the next. An early error propagates silently, and a correct answer reached via flawed logic evades outcome-level detection. In specialized domains, teacher LLMs err on intermediate steps, safety constraints restrict cloud distillation, and shifting conditions demand adaptation, leaving self-evolution as the practical route. Naive self-evolution can collapse: outcome-only rewards let the model exploit distributional shortcuts, and weak self-evaluation reinforces spurious paths into stable failure patterns. We exploit a key asymmetry: generating a correct chain is hard, but verifying a single step is easy. Many high-stakes domains admit a deterministic, queryable oracle, a physics simulator or rule engine over codified constraints. It checks asserted steps without teacher-level ability and abstains beyond its rules; it can check what the model asserts, never replace it. This enables CoEvo, an oracle-grounded self-evolution framework where a single model alternates between Proposer and Solver. As Solver, the model generates competing chains; intra-group debate exposes disagreement steps, a proxy for the capability boundary, and the oracle adjudicates them into process-level supervision. As Proposer, the same model constructs progressively harder scenarios inside oracle constraints, steering the curriculum toward deep multi-hop chains. Both roles are updated jointly, so training pressure co-evolves with the model. On industrial, clinical, and legal multi-step causal reasoning benchmarks, CoEvo enables an 8B LLM to sustain self-evolution, surpassing distillation baselines and the strongest proprietary reference on path correctness (82.1% vs. 71.4%). The trained model generalizes to unseen categories and systems, preserving root-cause accuracy.
Anomalous video understanding aims to identify abnormal events in videos and interpret their semantic meanings beyond simple anomaly detection. Recent video large language models (Video-LLMs) have demonstrated promising zero-shot capabilities for this task, yet their performance remains limited due to insufficient adaptation to diverse anomaly patterns and evolving environments. Test-time reinforcement learning offers a promising solution by enabling models to improve through self-generated feedback signals without requiring additional human annotations. However, applying it to anomalous video understanding remains challenging due to three issues: (1) generated pseudo-labels can be unreliable when consensus is weak; (2) binary reward designs fail to capture uncertainty in model generations, resulting in ineffective optimization signals; and (3) unanimous rollout groups receive identical rewards, causing group-relative advantages to collapse and eliminating effective policy-gradient signals. To address these challenges, we present a novel test-time reinforcement learning framework for anomalous video understanding by introducing dual-query consistency filtering, an entropy-aware consensus reward, and a virtual negative anchor mechanism. The framework retains reliable samples through consistency across semantically equivalent queries, combines answer agreement with generation uncertainty for reward estimation, and introduces a virtual negative anchor to create reward variation in unanimous rollout groups, thereby preserving effective group-relative optimization signals. Experiments on VAU-Bench show that our method outperforms the compared frozen and supervised baselines. The gains are most pronounced on the ECVA subset of VAU-Bench with thinking, where accuracy improves from 75.81% to 90.00% relative to the frozen backbone.
Large language models (LLMs) have been widely adopted as backbones for recommender systems. However, their language-centric pretraining makes it difficult to capture collaborative signals implicit in user-item interactions, which are crucial for personalized recommendation. Existing methods either inject collaborative representations produced by external recommenders or model only intra-sequence dependencies, limiting their ability to exploit global collaborative patterns. To address this limitation, we propose GALLM, a graph-aware LLM framework for sequential recommendation. GALLM constructs a collaborative graph over text tokens and item tokens, and models three types of relations: Text--Text relations for preserving semantic dependencies, Item--Text relations for aligning item tokens with their textual descriptions, and Item--Item relations derived from global item co-occurrence patterns. These relations are transformed into lightweight learnable attention biases and incorporated into the LLM attention mechanism, enabling collaborative-aware token interactions without introducing an additional graph encoder. Experiments on four real-world benchmarks show that GALLM achieves the best performance among the compared baselines, improving over the strongest baseline by 9.76\% on average in HR@5.
Autonomous AI agents tackling Long Horizon Tasks depend on marketplace skills that are certified one at a time: a scanner returns a safety verdict for each skill and declares the ecosystem safe if every package passes. We show that this assumption fails under skill composition. A skill may pass the per-skill scanner individually yet participate in a risky composition when an agent connects its outputs, capabilities, or side effects with those of other scanner-passing skills. This makes skill composition risk a path level property rather than a node level property, explaining why existing skill scanners that inspect individual packages achieve limited interception. To study this threat, we present CompoSkill, a framework that constructs skill composition attacks through a dual attacker system. The white-box attacker knows the victim's installed skill pool and directly injects explicit skill-id sequences; the black-box attacker knows only a role profile, downloads the top marketplace skills for that scenario, builds a Skill Composition Graph, and searches for high risk chains whose implicit lures never name skill identifiers. We further construct CompoSkill-Bench, a benchmark of 1,140 records built from long-horizon professional workflows across five threats and six scenarios on OpenClaw and Nanobot. CompoSkill achieves risk Chain Formation Rates (CFR) up to 83.3% in the white box setting and 80.6% in the black box setting, while existing skill scanners block only a limited fraction of the risky compositions. Finally, we observe a bridge-bonus-then-hop-decay pattern: a bridge skill can increase attack success, but Attack Success Rate (ASR) decreases once additional hops make the risk chain longer than three skills. These results expose a systematic gap in single skill certification for autonomous AI agents.
Patent retrieval and matching based on large language models (LLMs) play a vital role in intellectual property protection. However, due to the complex structure of patent documents, dense technical terminology, and multi-modal information, traditional methods struggle to accurately identify subtle differences between patents. Existing LLM-based patent matching approaches typically rely on domain-specific pretrained or instruction tuning, which often entail high manual labeling costs and catastrophic forgetting. While retrieval-augmented generation (RAG) methods introduce external knowledge they fail to fully leverage LLM's capability to automatically parse patents and mine deep semantic relationships. To address these limitations, this paper proposes a self-knowledge RAG framework that guides LLMs to autonomously extract key technical entities and construct hierarchical ontological structures from patent matching queries, thereby enabling query expansion and precise retrieval. The method integrates the FAISS retrieval with a generative matching mechanism, leveraging self-knowledge to enhance the model's understanding of patent innovations and significantly improve retrieval and matching accuracy. Experimental results demonstrate the outstanding performance of the proposed method on real-world patent datasets, validating its effectiveness and application potential.
Hierarchical Text Classification (HTC), as a critical text mining task, faces challenges such as complex label hierarchies and class imbalance. Existing methods based on large language models (LLMs) struggle to be efficiently applied to this task due to issues like lengthy prompts and loss of label structural information. To address these limitations, this paper proposes a weakly supervised HTC framework enhanced by LLM-based data augmentation. The framework first enriches the label hierarchy semantically through keyword generation and corpus mining, thereby enhancing the model's understanding of labels. Subsequently, it guides the LLM to generate pseudo-samples to mitigate the long-tail problem, and employs a Gaussian mixture model for confidence-based resampling to optimize the quality of generated data. Experimental results demonstrate that the proposed method effectively improves the reliability of LLM-generated pseudo-labels and significantly enhances classification performance on fine-grained and imbalanced datasets.
Video coding is advancing into the low and ultra-low bitrate regime, driven by end-to-end codecs that replace the hand-crafted pipeline with jointly optimized neural networks and generative codecs that exploit the priors of video generation models. Yet the dominant metrics, LPIPS and DISTS, measure feature and texture similarity rather than content fidelity: a reconstruction that hallucinates a wrong face or blurs text into convincing strokes can still score well, even when a human rejects it instantly. To address this, we propose CodecArena, the first vision-language framework for video coding quality assessment, casting codec evaluation as source-conditioned comparative reasoning between a reference and its reconstructions. We optimize CodecArena with Facet-GRPO, a visual reinforcement learning scheme that aligns pairwise codec preferences while grounding the verdict in five fidelity facets: identity, objects, text, texture, and temporal consistency. Its facet-anchored reward uses automatically derived facet directions as weak anchors, rather than human per-facet labels, to prevent any single sub-score from dominating the holistic preference and to yield interpretable fine-grained quality judgments. To support training and evaluation in this underexplored regime, we construct two complementary resources: CodecArena-1K, a fully automatic preference dataset of 1,500 comparison groups built from traditional, neural, and generative codec reconstructions with fused vision-language and objective supervision; and CodecArena-Bench, a human-ranked benchmark with source-disjoint videos for fair out-of-domain evaluation. Extensive experiments demonstrate that CodecArena achieves state-of-the-art agreement with human judgments on source-disjoint content across diverse codecs and bitrates, surpassing perceptual metrics and prior vision-language evaluators.
Traditional whole slide image (WSI) analysis methods typically rely on the multiple instance learning (MIL) paradigm, which extracts patch-level features at high magnification and aggregates them for slide-level prediction. However, such exhaustive patch-level processing is computationally expensive, severely limiting the efficiency and scalability of WSI analysis. To address this challenge, we propose PathCTM (a Pathology-oriented Continuous Thought Model) that enables token-efficient scale-space continuous reasoning for gigapixel WSIs. PathCTM formulates diagnostic inference as a dynamic sequential information pursuit. It progressively transitions from low-magnification global to high-magnification local inspection, and adaptively terminates inference when sufficient evidence is gathered to effectively bound decision uncertainty. Specifically, it uses conditional computation for dynamic scale switching with attention-guided region pruning, coupled with confidence-aware early stopping. Extensive experiments demonstrate that, compared with standard MIL-based methods, PathCTM reduces the number of required image patches by 95.95% and shortens inference time by approximately 95.62%, while maintaining AUC without degradation. Code is available at https://github.com/JSGe-AI/PathCTM.
Multiview image-based 3D visual grounding predicts a coordinate frame to define a coordinate system and then regresses a 3D bounding box for localization. However, existing methods jointly optimize coordinate frame selection and box regression, leading to coordinate-relative box ambiguity and degraded grounding performance. This ambiguity arises because the same box admits different numerical representations across coordinate frames, creating multiple optimization targets and yielding invalid compromise predictions. To tackle this challenge, we propose CoordRefer, a coordinate-aware framework that decouples coordinate frame selection from coordinate-conditioned grounding. CoordRefer first selects a reference frame to define the coordinate system and then conditions 3D box prediction on the coordinate system. We perform coordinate-aware supervised fine-tuning to establish coordinate frame selection and coordinate-conditioned box regression, followed by Group Relative Policy Optimization with 3D IoU-based rewards to align both stages with downstream grounding quality. On ScanRefer with Qwen3-VL-2B, CoordRefer achieves gains of 11% in Acc@0.25 and 7% in Acc@0.5 over the coordinate-agnostic baseline, while its geometrically refined variant surpasses methods using explicit 3D inputs.
Video world models predict future observations conditioned on historical observations and control signals, enabling long-horizon generation through autoregressive state transitions. Unlike conventional video generation models that primarily capture visual appearance and motion, video world models learn the underlying dynamics governing environment evolution under agent actions, providing a foundation for embodied AI and interactive simulation. Recent progress has largely relied on adapting pretrained video generation models through post-training or distillation. Although effective, these approaches often require complex training pipelines, substantial computational resources, and suffer from the mismatch between bidirectional pretraining and causal streaming inference. Recent studies have shown that training autoregressive video world models from scratch is feasible and scalable. However, the community still lacks a lightweight, transparent, and fully reproducible baseline trainable end-to-end with modest computational resources. We present MiniWorld, a reproducible framework for training streaming video world models from scratch. MiniWorld employs a block-causal Video Diffusion Transformer trained with Flow Matching in the latent space of a pretrained Video VAE. Building on Diffusion Forcing, it adopts a chunk-wise non-decreasing noise schedule and two-stage continued training to improve temporal modeling and stability. During inference, MiniWorld combines a rolling KV cache with pipelined asynchronous denoising for efficient streaming generation under bounded computation. The entire model can be trained within several days on a single 8-GPU server. By releasing the training and inference codebase and pretrained checkpoints, we hope MiniWorld will facilitate future research on video world modeling.