Search arXiv⌕ Search

arXiv subjects

Yang Li

Publications and source records attributed to Yang Li.

At least 55 records · Page 3Linked to original sources
arXiv2026

PTGPO: Prefix Tree Group Policy Optimization

Training language agents on long-horizon interactive tasks is challenging because sparse terminal rewards provide weak credit signals for intermediate actions. Existing group-based methods either assign a shared trajectory-level advantage or estimate step-level advantages from state groups, which may conflate the current action with subsequent decisions. We propose Prefix Tree Group Policy Optimization (PTGPO), a critic-free method that constructs prefix trees over trajectory suffixes within anchor-state groups. PTGPO assigns each tree edge a credit given by the difference between its child and parent empirical mean returns, capturing the conditional return change revealed by each additional action. These prefix-tree credits provide fine-grained learning signals without requiring a critic or additional rollouts. Experiments on interactive benchmarks ALFWorld, WebShop and Sokoban show that PTGPO consistently improves over RL baselines, demonstrating its effectiveness.

cs.LG↗
arXiv2026

HYDRA: Representation Harmonized Tokenization for Multimodal Generation and Understanding

Unified Multimodal Models struggle to bridge the fundamental gap between the abstract representations needed for visual understanding and the detailed primitives required for generation. Existing approaches typically compromise by employing decoupled encoders, stacking representation encoder atop VAEs, or utilizing discrete quantization. However, these methods often disrupt information coherence and lead to optimization conflicts. To this end, we introduce HYDRA-TOK, a representation-harmonized pure ViT in the insight that visual modeling should evolve from generation to understanding. HYDRA-TOK reformulates the standard backbone into a progressive learner that transitions from a Gen-ViT, which captures structure-preserving primitives, to a Sem-ViT for semantic encoding. Crucially, this transition is mediated by a Generation-Semantic Bottleneck (GSB), which compresses features into a low-dimensional space to filter noise for robust synthesis, then restores dimensionality to empower complex semantic comprehension. Built upon this foundation, we present HYDRA, a native unified framework integrating perception and generation within a single parameter space. Extensive experiments establish HYDRA as a new state-of-the-art. It sets a benchmark in visual reconstruction (rFID 0.08) and achieves top-tier generation performance on GenEval (0.86), DPG-Bench (86.4), and WISE (0.53), while simultaneously outperforming previous native UMMs by an average of ~10.0 points across eight challenging understanding benchmarks.

cs.CV↗
arXiv2026

VIS-Ground: Video Interactive Storytelling with Contextual Grounding

Video interactive storytelling enables viewers to actively steer how a video unfolds. However, once we allow viewers to intervene during generation, a new challenge arises: The viewer's request can have latent dependencies on both the grounding source and the current rendered video state. These dependencies may not be explicitly stated in any individual input, but emerge only when the source, rendered history, and new viewer intent are considered jointly. Existing interactive video generation systems primarily emphasize following viewer instructions, while source-grounded video generation methods focus on aligning generated content with an external narrative or knowledge source. This leaves a fundamental question underexplored: What context should a generation model ground on during interactive continuation, and how can heterogeneous, unstructured inputs be transformed into such grounding context? In this work, we formulate contextual grounding as the process of transforming heterogeneous input context into an executable constraint model for video generation. To address this challenge, we introduce VIS-Ground, which performs Structured Context Abstraction to recover grounded states and cross-context dependencies, Generation Constraints Induction to project relevant dependencies into candidate-specific constraints, and Constrained Video Generation to enforce these constraints through planning, verification, revision, and rendering. Across three video generation backbones, VIS-Ground consistently achieves the highest overall composite score, reaching an average absolute improvement of 10.3 points over the strongest per-backbone baselines. Detailed analysis further shows gains across both narrative and knowledge grounding, and reveals remaining challenges in dependency extraction, and faithful realization during video rendering.

cs.CV↗
arXiv2026

How Anthropomorphic Attitudes Toward Agents Divide User Behavior, and How Design Should Change

Studies of conversational agents rely on interviews, surveys, lab tasks, or taxonomies. Whether anthropomorphic naming splits those patterns, and whether replies should change, lack field evidence. We report a field study of a desktop assistant (May-August 2026; n=257). Stance is an anthropomorphic assistant name (118 users; 45.9%). Behavior comes from a 128-unit sparse-autoencoder codebook, identity tags, and opening lexicons. Ranks differ by stance (Spearman rho=+0.249 vs. null mean +0.382; p=.0419). Teacher and tutoring identities covary with renaming, an introverted task-only orientation against it; renamers greet more and command less; confiding shows the codebook's largest gap. We revise the agent: greet and receive affect on relational openings, execute directly on tasking. In 1,744 judgments (n=129), renamers chose the revised reply far more often than default-name users on being treated as a person and having affect received, less robustly on willingness to continue, and neither judged it worse on task interference.

cs.HC↗
arXiv2026

Hypergraph-Enhanced Dual Convolutional Network for Bundle Recommendation

Bundle recommendation ranks sets of related items rather than isolated items. Its central challenge is to connect user preferences, item interactions, and bundle composition without losing the signals needed to rank bundles. We propose Hypergraph-Enhanced Dual Convolutional Neural Network (HED), which constructs a complete hypergraph containing user--bundle, user--item, and bundle--item interactions together with intra-user and intra-bundle relations. HED couples complete-hypergraph propagation with a user--bundle branch, allowing item-aware higher-order context to inform ranking while preserving recommendation-specific signals. On NetEase, HED-128 improves over the strongest baseline by 5.04--6.97% across the six reported metrics; on Youshu, HED-64 improves by 1.87--4.56%. Ablation results support the contributions of both the user--bundle branch and intra-type relations, and sensitivity analyses identify stable operating ranges for the main hyperparameters. We further quantify the computational trade-off of the complete hypergraph, including its memory cost. The evidence supports HED on the two evaluated bundle-recommendation datasets while making its resource limitations explicit. Code and datasets will be made available upon publication.

cs.IR↗
arXiv2026

Zero-shot Video Moment Retrieval via Off-the-shelf Multimodal Large Language Models

The target of video moment retrieval (VMR) is predicting temporal spans within a video that semantically match a given linguistic query. Existing VMR methods based on multimodal large language models (MLLMs) overly rely on expensive high-quality datasets and time-consuming fine-tuning. Although some recent studies introduce a zero-shot setting to avoid fine-tuning, they overlook inherent language bias in the query, leading to erroneous localization. To tackle the aforementioned challenges, this paper proposes Moment-GPT, a tuning-free pipeline for zero-shot VMR utilizing frozen MLLMs. Specifically, we first employ LLaMA-3 to correct and rephrase the query to mitigate language bias. Subsequently, we design a span generator combined with MiniGPT-v2 to produce candidate spans adaptively. Finally, to leverage the video comprehension capabilities of MLLMs, we apply VideoChatGPT and span scorer to select the most appropriate spans. Our proposed method substantially outperforms the state-ofthe-art MLLM-based and zero-shot models on several public datasets, including QVHighlights, ActivityNet-Captions, and Charades-STA.

cs.MM↗
arXiv2026

Uniqueness of tangent cones with immersed special Legendrian links

Under the assumption of integrability of the smooth Jacobi fields and a condition on the intersection pattern of the link, we prove uniqueness of special Lagrangian tangent cones in $\mathbb{C}^3$ whose links are compact immersed special Legendrian surfaces with transverse double points. The proof is based on a discrete Lojasiewicz type inequality, which comes from a gluing obstruction mechanism.

math.DG↗
arXiv2026

VOMMI: Collecting and Leveraging Portable Demonstrations for Mobile Manipulation

Portable mobile-manipulation demonstrations can help alleviate data scarcity for embodied intelligence, but obtaining reliable, low-cost, and robot-free motion supervision from RGB observations remains challenging. Existing approaches often rely on teleoperation or specialized devices equipped with additional sensing hardware, while directly using estimated visual odometry (VO) trajectories can introduce inconsistencies due to accumulated drift and imperfect motion supervision. We present the Visual-Odometry-Conditioned Mobile Manipulation Interface (VOMMI), a portable demonstration collection and learning framework that connects portable RGB demonstrations to vision-language-action (VLA) post-training through offline trajectory reconstruction and online visual-motion conditioning. VOMMI synchronizes body and hand views to capture navigation context and local object interactions without requiring human-robot kinematic correspondence calibration. R2-VO refines offline demonstration trajectories using sparse geometric anchors and produces causal local-motion tokens over multiple prediction horizons for online policy conditioning. An action-group residual adapter incorporates these tokens only into the base branch. Experiments use a 500-trajectory portable for each task, with 75 trajectories held out for RGB-VO evaluation, and 200 robot demonstrations as references. Our policy, post-trained only on portable demonstrations, achieves 18.2% lower base-velocity error than a policy trained with robot-collected demonstrations, while maintaining comparable end-effector translation accuracy. Offline reconstruction reduces absolute trajectory errors for the body and hand streams by 24.6% on average relative to the best evaluated baseline for each stream. The complete system improves the mean success rate by 8.3 percentage points over OpenPI 0.5 across three real-robot tasks.

cs.RO↗
arXiv2026

ReCoVR: Closing the Loop in Interactive Composed Video Retrieval

Composed video retrieval (CoVR) searches for target videos using a reference video and a modification text, but existing methods are restricted to a single interaction round and cannot support the progressive nature of real-world visual search. To bridge this gap, we first formalize interactive composed video retrieval, a multi-turn extension of CoVR, where users progressively refine their search intent through natural-language feedback across turns. Adapting existing interactive retrieval methods to this setting reveals two structural weaknesses: reliance on a single retrieval channel and an open-loop retrieval design that consumes user feedback but does not diagnose whether its own retrieval trajectory is drifting or stagnating. To address these limitations, we propose ReCoVR (Reflexive Composed Video Retrieval), a dual-pathway architecture built on reflexive perception, where the system treats its retrieval history as diagnostic evidence alongside user feedback. Specifically, an Intent Pathway routes heterogeneous feedback to complementary retrieval channels, while a Reflection Pathway performs trajectory-level reflection to monitor result evolution and correct retrieval errors across turns. Experiments on multiple benchmarks show that ReCoVR consistently outperforms interactive baselines, notably achieving 74.30% R@1 after just one interactive round on the WebVid-CoVR-Test dataset.

cs.IR↗
arXiv2026

Symmetries on vector parking functions via bounded lattice paths

Partly motivated by enumeration of parking functions and their variants, there is a long-standing interest in lattice paths refined by several statistics, including the notable $\mathsf{run}$ and $\mathsf{return}$. We consider bounded lattice paths, which are bounded by a given lattice path and are related to vector parking functions, for which we generalize $\mathsf{run}$ to composition runs, parameterized by a composition. By constructing involutions on these paths, we establish symmetries relating composition runs to some generalized return statistics. As an application, we settle an open problem of Dai, Fu, and Qiu on rational Dyck paths. The symmetries between generalized $\mathsf{run}$ and $\mathsf{return}$ are then transferred to vector parking functions, which suggest a new notion of prime decomposition. In the special case of $(a, b)$-parking functions, we compute the generating function refined by $\mathsf{run}$ and $\mathsf{pri}$, which is new even for classical parking functions.

math.CO↗
arXiv2026

Nuclear structure functions and EMC effect in a relativistic deuteron

We investigate the longitudinal momentum distributions (LMDs) of the deuteron using a relativistic deuteron wave function derived from a realistic nucleon-nucleon (NN) interaction within the light-front framework. By convoluting the deuteron LMDs with the nucleon parton distribution functions (PDFs), we analyze the unpolarized, longitudinally polarized, and tensor-polarized structure functions of the deuteron. In addition, we also study the EMC effect in the weakly bound deuteron through the structure function ratio $F_{2}^{D}/(F_{2}^{p}+F_{2}^{n})$, which deviates from unity due to nuclear binding and Fermi motion effects.

nucl-th↗
arXiv2026

Self-Evaluating Recursive Agents

Recursive language-model agents decompose tasks and delegate subtasks to child instances of the same policy, forming a tree of work. Training them, however, is hard: the final outcome is verifiable, but the self-invented intermediate subtasks are numerous and carry no ground truth. Existing methods score each node with a verifier or judge, which is costly at scale and blind to decomposition quality. We argue that a recursive agent must learn three coupled capabilities within one set of weights: decomposing problems into subtasks, solving them, and evaluating the outcomes, each requiring its own training signal. SERA (Self-Evaluating Recursive Agents) turns evaluation into a learned capability of the policy itself. Before delegating, the parent writes a rubric of weighted success criteria for each child subtask; a ranking objective against verified outcomes then trains rubric generation so that the criteria track genuine subtask success. In addition, a complementary leaf-coverage signal provides direct credit for task decomposition. Our central finding is that \emph{training} the policy to generate aligned rubrics is what drives the gains: because the same weights both evaluate and execute, learning to judge subtasks sharpens the agent's ability to solve them. Notably, external supervision is also reduced: the judge is consulted only to train the rubric generator, while solving is trained against the agent's own rubric scores, which outperform direct use of the judge. Beyond training, the learned rubric doubles as an inference-time selector for tree search. On TextCraft-Synth and TextWorld-Sync, SERA improves over strong recursive-agent baselines by 5.38 and 13.14 points on average, and rubric-guided tree search at inference adds a further 2.43 points on TextWorld-Sync.

cs.AI↗
arXiv2026

Reducing Cognitive Overhead in Tool Use via Multi-Small-Agent Reinforcement Learning

Recent advances in multi-agent systems highlight the potential of specialized small agents that collaborate via division of labor. Existing tool-integrated reasoning systems, however, often follow a single-agent paradigm in which one large model interleaves long-horizon reasoning with precise tool operations, leading to cognitive-load interference and unstable coordination. We present MSARL, a Multi-Small-Agent Reinforcement Learning framework that explicitly decouples reasoning from tool use. In MSARL, a Reasoning Agent decomposes problems and plans tool invocations, while multiple Tool Agents specialize in specific external tools, each trained via a combination of imitation learning and reinforcement learning with role-specific rewards. On mathematical problem solving with code execution, MSARL significantly improves reasoning stability and final-answer accuracy over single-agent baselines. Moreover, the architecture generalizes to diverse tool-use tasks, demonstrating that cognitive-role decoupling with small agents is a scalable blueprint for multi-agent AI design.

cs.AI↗
arXiv2026

Exploring Forum Post Retrieval with Generative Modeling

Generative recommendation (GR) has emerged as an alternative to embedding-based retrieval, building on the success of generative models in language and vision. We are exploring GR on Facebook Forum, a standalone application for medium-to-heavy users of Facebook Groups. Because Forum is a new surface, its own interaction data are too sparse to train a GR model from scratch. We address this with transfer along two axes: we train on a broader corpus of Facebook Groups engagements rather than Forum sessions alone, and we reuse hierarchical, prefix-based semantic IDs (SIDs) learned from cross-platform Facebook Feed data instead of fitting a Forum-specific tokenizer. A 3B-parameter instruction-tuned language model is then supervised-fine-tuned to generate SIDs directly from user context. We systematically ablate the design choices that matter most in practice, including SID construction, the composition and length of user history, and the inclusion of user-profile features. Our results show that cross-platform SIDs transfer to a new recommendation surface, and offer practical guidance for teams deploying GR on real-world social platforms.

cs.IR↗
arXiv2026

From Hidden Zeros to Exact Splittings and New Zeros

Hidden zeros impose constraints on scattering amplitudes beyond their familiar factorization properties. We explore their structure in two related directions. We first promote hidden zeros to explicit splitting formulas that organize full amplitudes at generic kinematics. Ordered $\mathrm{Tr}(ϕ^3)$ amplitudes, nonlinear sigma model (NLSM) amplitudes, and cosmological wavefunctions share the same defining exact splitting structure $\mathcal A=\sum_αR_α\, {\mathcal J}_{α,L}{\mathcal J}_{α,R} {\mathcal J}_{α,\mathrm{out}}$, adapted to any hidden zero. Each prefactor $R_α$ is a condition of the hidden zero locus, so this decomposition manifests the hidden vanishing term by term. The remaining factors are lower point amplitudes or currents. Using these representations, we can systematically find new zero loci beyond the usual ones. In particular, we obtain five new all-multiplicity zero families. We also find continuous families of zeros: the coefficients of their defining equations can vary continuously while the amplitude remains zero.

hep-th↗
arXiv2026

RoboHarn-Evo: Evolving Hierarchical Physical Knowledge for Self-Improving Robotic Manipulation

Vision-language models can coordinate long-horizon robot manipulation, yet successful task reasoning still depends on whether local physical interactions produce the intended effects. We study how repeated interaction can improve this capability without updating the base model. We introduce RoboHarn-Evo, a dual-loop harness that evolves Hierarchical Physical Knowledge (HPK) from physical experience. HPK couples two levels of reusable knowledge: Task Knowledge captures which subtask should be executed and when it is complete, while Action Knowledge captures object-relative geometric strategies and their physical effects. During execution, the agent retrieves knowledge at the corresponding decision level and grounds it in the current scene under the task goal. Across episodes, physical feedback is used to revise historical knowledge, update its applicability, and organize reusable entries for subsequent retrieval. Experiments on RMBench show that HPK improves average success by up to 24.2 percentage points across different agent models. With 80 interaction rollouts, held-out success rises from 48.3% to 75.0% for GPT-5.5 and from 70.0% to 88.3% for GPT-6. RoboHarn-Evo also resolves over 83% of historical knowledge errors while retaining 95.8% of valid knowledge, and transfers zero-shot from RMBench to RoboDojo with gains of 35.0 and 25.0 percentage points. These results demonstrate that physical interaction can be accumulated into reusable knowledge for improving subsequent manipulation.

cs.RO↗
arXiv2026

Diagnosing On-Policy Self-Distillation for Reasoning Language Models

On-policy self-distillation (OPSD) has attracted growing interest as a promising approach to improve the reasoning ability of language models. Without external rewards nor a separate stronger teacher, the self-teacher with privileged information could provide dense signals on student's trajectories. However, its behavior in language reasoning remains unclear, with reported outcomes ranging from modest gains to behavioral collapse. In this work, we diagnose OPSD for mathematical reasoning across models spanning 0.6B--8B parameters. We conduct controlled experiments and token-level analyses to fully delve into OPSD. We point out that teacher's signal is shaped by reasoning-mode alignment and the complete teacher prefix, rather than by privileged semantics alone. OPSD improves reasoning only in narrow compatibility regimes. Otherwise, it produces ineffective length growth, stable degradation, or behavioral collapse. Token-level analysis shows that teacher's signal is not stable and does not predict downstream performance. Based on these results, we argue that OPSD is a sensitive algorithm rather than a generally reliable reasoning-improvement post-training method.

cs.CL↗
arXiv2026

FORTE: Adaptive Scoring and Exact Keyframe Selection for Long-Video Question Answering

Query-aware keyframe selection enables multimodal large language models (MLLMs) to process long videos using only a small set of question-relevant frames. Existing score-based methods, however, typically search within a fixed, uniformly sampled candidate pool, preventing evidence outside this pool from ever being selected. Given a limited relevance-scoring budget, the key challenge is to allocate evaluations adaptively to promising frames while continuing to explore underrepresented temporal regions. We introduce FORTE, a training-free framework that addresses this challenge through two stages: adaptive relevance scoring and global keyframe optimization. Starting from sparse, uniformly distributed observations, our efficient Gaussian-process relevance predictor estimates relevance for unscored frames, exploiting temporal locality and the approximately banded kernel structure to reduce the core computation from cubic to linear time in the number of frames for fixed bandwidth. The scoring stage then selects which frames to score next by balancing predicted relevance with temporal coverage, prioritizing promising regions while also exploring less-represented parts of the video. The optimization stage selects the final keyframes by maximizing an objective that jointly captures measured relevance and temporal coverage. We derive an exact algorithm that leverages the logarithmic coverage structure to identify the optimal subset of the scored candidate pool in time linear in the pool size, for a fixed final-frame budget. Experiments on four long-video question-answering benchmarks show that FORTE achieves the highest observed mean accuracy among the compared selectors under every tested scoring budget. Further evaluations demonstrate its consistent effectiveness across different relevance scorers and downstream MLLMs.

cs.CV↗