Searcharxiv⌕ Search

arXiv subjects

Qi Chen

Publications and source records attributed to Qi Chen.

At least 37 records · Page 2Linked to original sources
arXiv2026

OmniVChat: Synthesizing, Benchmarking, and Training for Native Audio-Visual Dialogue

We define OmniVChat (Omni Video Chat) as the task of native audio-visual dialogue between a user and an omni model. In OmniVChat, omni models directly and simultaneously receive audio and video from a user and return text. The user's query is embedded in the audio and video, without a separate text question, external captioning, or speech recognition. Direct audio-visual input reduces external latency and computation while preserving perceptual cues. However, research on OmniVChat faces two constraints: data availability and evaluation. Recordings of people using their own devices are scarce. Furthermore, good replies often depend on multimodal context and can be phrased in many ways, making keyword matching unreliable for evaluation. Recent progress in agent systems and video generation makes generation for comprehension viable, which means using synthesized dialogues for training and evaluation. Therefore, we present OmniVChat-Studio, a multi-agent data engine for synthesizing single- and multi-turn audio-visual dialogues. We use synthesized dialogues to build OmniVChat-Bench, an evaluation benchmark that evaluates omni models' basic dialogue abilities across five ability categories. Replies are judged by a large language model based on explicit scoring criteria. We also present OmniVChat-RL, a reinforcement learning reward design that jointly targets reply correctness, efficiency, and style in OmniVChat. Training Qwen3-Omni-Instruct with OmniVChat-RL on synthesized dialogues improves its performance on both OmniVChat-Bench and the human-recorded OmniVChat-Bench-Human. These gains validate the reward design and show transfer to real-world dialogues in training and evaluation.

eess.AS↗
arXiv2026

When the Score Becomes the Target: Rethinking Metric Validity in Autonomous Driving

Driving benchmark scores are increasingly used not only for evaluation but also as optimization targets. This raises a fundamental question: do score gains remain reliable evidence of driving improvement once the score itself is optimized? We address this question by examining how the scoring process responds to changes in driving behavior and whether the resulting gains persist under repeated execution and replanning. We decompose the process into execution, measurement, subscore mapping, and aggregation. Controlled interventions reveal substantial behavioral changes that receive little score response because distinctions are omitted, thresholded, or attenuated between requested and executed motion. Closed-loop comparisons further show that optimization gains can reverse when the execution interface changes, demonstrating their dependence on how requests are executed and returned as feedback. Together, these findings connect the behavioral distinctions preserved by a metric to the conditions under which its gains transfer. Metric validity under optimization therefore requires examining both what the scoring process measures and how the optimized behavior is executed.

cs.CV↗
arXiv2026

SolveEdit: Benchmarking Visual Problem Solving in Generative Models

Machine intelligence is often evaluated through abstract reasoning problems, yet many real-world problems are visual, such as arranging objects, repairing layouts, or tracing routes. Solving these problems requires understanding a scene, inferring what must change to achieve a goal, and realizing that change without disturbing unrelated content. However, existing benchmarks mainly evaluate perception, generation, or explicitly specified transformations, leaving goal-driven visual problem solving underexplored. To bridge this gap, we introduce SolveEpIT, a benchmark for visual problem solving through scene transformation. Given an image and a goal, a model must infer a valid transformation from the request, the scene, or a visually expressed rule, then execute it while preserving unrelated content. SoLvEEDrr contains 2,728 cases. Atomic transition contracts specify required and protected conditions, enabling SoLvEScoRE to measure completion and unintended changes without a single reference output. The strongest evaluated model achieves only57.0% SolvEScore. We further introduce SolveEdiT-PLAN, a two-stage visual planner that instantiates the transition before generation. Under matched single-generation evaluation, it improves SoLvEScoRE by 9.1 points on average across three tested generators, including a gain from 57.0% to 71.6% for GPT-Image-2, without modifying the editor.

cs.CV↗
arXiv2026

CyberClear: A Benchmark for LLM Agent Systems on APT Attack Chain Provenance

Large language model agents have demonstrated promising capabilities in cybersecurity tasks, yet their ability to reconstruct complete Advanced Persistent Threat attack campaigns from complex security logs remains largely unexplored. Existing cybersecurity benchmarks for agents mainly focus on vulnerability discovery, exploitation, and security analysis tasks, leaving the evaluation of attack chain provenance under realistic security logs insufficiently studied. To address this gap, we introduce CyberClear, a benchmark for evaluating LLM agents and advanced agent systems on APT attack chain provenance from long-context security logs. CyberClear covers both single-step attacks and multi-stage attack chains, requiring agents to identify attack evidence, infer attack progression, and generate provenance graphs containing entities, causal relationships, MITRE ATT&CK techniques, and forensic evidence. To enable comprehensive evaluation, we develop an evaluation method tailored to APT attack chain provenance. Unlike conventional text similarity metrics that focus on surface-level matching, our evaluation examines whether reconstructed graphs preserve the semantics of attack chains across single-step behavior correctness, multi-step behavior identification, temporal and causal consistency, entity and relationship fidelity, and overall attack narrative consistency. Advanced multi-agent systems powered by state-of-the-art LLMs still struggle on CyberClear, motivating us to propose CyberProvenance, an agent cyber harness designed for multi-agents that augments LLM agents with evidence accumulation, execution-based validation, and feedback-guided refinement mechanisms for reliable attack-chain provenance. Extensive evaluations on CyberClear demonstrate the effectiveness of CyberProvenance in improving evidence reasoning, execution-grounded validation, and complete APT attack chain reconstruction.

cs.CR↗
arXiv2026

Negative Rank Relations for Giant Graviton Correlators

We study correlation functions of giant and dual giant gravitons in $\mathcal N=4$ super Yang--Mills theory. Although the two objects correspond to rather different D3 brane configurations in $AdS_5\times S^5$, their gauge theory operators are Schur polynomials associated with transposed Young diagrams. We show that this transposition is accompanied by a formal rank reflection $N\to -N$ at the level of correlation functions. For both $U(N)$ and $SU(N)$, the relation is exact for free correlators at finite $N$, and, using Lagrangian insertion, extends to separated point weak coupling integrands at every loop order. More generally, it applies to any number of Schur polynomial external operators, provided all Young diagrams are transposed. We illustrate the relation in several examples and also discuss evidence for its extension beyond perturbative integrands.

hep-th↗
arXiv2026

Omni Demand Understanding: A Benchmark for Contextual User-Intent Inference in Multimodal Interaction

Natural audio-visual interaction is emerging as an important interface for AI assistants, allowing users to communicate through speech and vision rather than carefully composed text prompts. However, existing benchmarks of interactive capabilities still focus primarily on response quality, leaving a more fundamental question underexplored: can a model correctly infer the user's underlying demand from complex multimodal interaction? Real-world user demands are often underspecified in speech and must be inferred from multimodal cues and dialogue history. This inference is further complicated by ambiguous or disfluent expression and noisy acoustic environments. Conversely, request-like speech may not constitute a demand to the assistant, leading to false triggers. We establish Omni Demand Understanding (ODU) as a distinct multimodal contextual inference problem: given an interaction stream, a model must detect whether a user demand is present and infer intent from multimodal and conversational context. ODU evaluates this capability along five dimensions, covering both single-turn and multi-turn interactions. We construct ODU-Bench using a challenge-driven taxonomy, taxonomy-guided agentic video generation, and human-recorded interactions, followed by media-grounded annotation and human verification. We evaluate 14 native MLLMs. Even the strongest, Gemini 3.1 Pro, recovers only 44.7% of key information that must be inferred from visual, acoustic, or conversational context. Moreover, 11 of the 14 models exhibit false-trigger rates above 50% on non-demand scenarios. These results reveal a systematic capability gap in current MLLMs' ability to infer contextual user demands. We hope ODU can establish the evaluation of a previously underexplored yet essential capability in multimodal interaction: correctly understanding user demands before generating an appropriate response.

cs.CL↗
arXiv2026

Tele-Traversability: Rethinking Traversability for Teleoperated Ground Robots in Terrain Navigation

Teleoperation, a human-in-the-loop control scheme, allows a human operator to remotely command and guide a mobile robot to navigate in off-road environments, yet fluent and user-friendly tele-navigation requires an alignment of traversability evaluation between human and robot. In the teleoperation system, the human operator typically utilizes off-site incomplete and delayed feedback via a human-machine interface to make a judgment of traversability, while the robot makes such an evaluation based on in situ onboard sensory information, which could cause divergent traversability estimation and thus generate mismatched decisions and actions. Existing approaches for traversability modeling, estimation, and prediction are mainly derived from the view of robots, i.e., robot-centric, and are practically suitable for fully autonomous mobile robots, but neglect the influence of human operators. To address this problem, this paper extends the concept of traversability from robot-centric to human-centric by accounting for the operator's cognitive states, such as attention, workload, and risk tolerance or awareness, termed tele-traversability. We first revisit the definitions and roles of traversability in robotics and then extend them to teleoperation settings. Finally, we highlight future trends and open challenges of tele-traversability toward human-centric teleoperation systems.

cs.RO↗
arXiv2026

Generalization in VAE and Diffusion Models: A Unified Information-Theoretic Analysis

Despite the empirical success of Diffusion Models (DMs) and Variational Autoencoders (VAEs), their generalization performance remains theoretically underexplored, especially lacking a full consideration of the shared encoder-generator structure. Leveraging recent information-theoretic tools, we propose a unified theoretical framework that provides guarantees for the generalization of both the encoder and generator by treating them as randomized mappings. This framework further enables (1) a refined analysis for VAEs, accounting for the generator's generalization, which was previously overlooked; (2) illustrating an explicit trade-off in generalization terms for DMs that depends on the diffusion time $T$; and (3) providing computable bounds for DMs based solely on the training data, allowing the selection of the optimal $T$ and the integration of such bounds into the optimization process to improve model performance. Empirical results on both synthetic and real datasets illustrate the validity of the proposed theory.

cs.LG↗
arXiv2026

LANTERN: A Closed-Loop Benchmark for VLM-Based Cooperative Driving with Temporally Grounded Warnings

We present LANTERN, a closed-loop benchmark for temporally grounded cooperative warnings. LANTERN separates warning onset, hazard onset, warning termination, and post-hazard recovery, and evaluates each physical event under matched warning and no-warning executions so that the warning's contribution is measured in isolation rather than confounded with onboard vision. The benchmark spans six safety-critical scenario families and provides 3,272 sequences with 236,309 frames for training, together with 120 matched route pairs for closed-loop evaluation. Each hazard route is evaluated under the warning and no-warning conditions, while its no-hazard control penalizes unconditional braking. We further introduce the Cooperative Unified Score (CUS), a safety-gated metric that jointly rewards route progress, anticipation, clearance, and recovery. Fine-tuning a representative VLM driving model raises CUS from 34.6 without warnings to 75.5 with them, demonstrating both the value of cooperative warnings and the discriminative power of the paired protocol. All resources will be made publicly available.

cs.RO↗
arXiv2026

RefGuard: Identity-Aware Language-Guided Robot Manipulation via Joint Target-Anchor-Frame Grounding

Vision-language-action (VLA) models have substantially advanced language-guided robot manipulation, yet reliable execution still hinges on identifying which physical object an instruction refers to. In cluttered scenes containing repeated objects, ambiguous anchors, or frame-dependent spatial terms, a robot can execute a geometrically valid action on a semantically compatible but unintended instance; we call this failure an identity switch. The referent is jointly determined by three coupled latent variables: the target, the anchor, and the reference frame, so committing to any one of them before execution turns residual ambiguity into a silent and irreversible error. We propose RefGuard, an identity-aware grounding framework that delays commitment by maintaining a joint posterior over all three variables. RefGuard builds a frame-conditioned object-centric scene graph from RGB-D observations, separating frame-independent geometry from directional relations, and routes the posterior through a decision policy that executes, clarifies, reobserves, or aborts. On a real UF850 arm, RefGuard records no identity switch on any ambiguity-stress trial and executes correctly on 90.0% of them, whereas fine-tuned VLA and LLM (Large Language Model)-based baselines switch identity in 33-46% of the same trials, while retaining 93.3% success on unambiguous scenes and recovering from post-grounding scene changes in 86.7% of trials. On a 3200-episode procedural suite, it raises correct execution on solvable instructions from 56.6% to 80.5% over the ablation that commits to the anchor and frame before the target, while deferring less often (19.5% vs. 43.4%).

cs.RO↗
arXiv2026

Aker: Density-Aware Approximate Caching for Vector Search (Extended Version)

Disk-based approximate nearest neighbor search (ANNS) incurs high I/O overhead due to frequent disk accesses during index traversal. Approximate caching, which reuses the results of past queries to serve future similar queries, offers a promising approach to bypass expensive disk searches. However, existing approaches suffer from two key limitations. First, their approximate hit predicates fail to simultaneously achieve high throughput and high accuracy, as they do not adapt to the varying local neighbor density in high-dimensional spaces. Second, they lack an effective refresh mechanism to maintain cache correctness under vector updates. We present Aker, an approximate cache for disk-based ANNS. Aker addresses these limitations through two core design choices. First, we introduce a per-query similarity threshold, where each cache entry maintains its own threshold that is dynamically adjusted based on observed cache hit patterns. This design enables Aker to adapt to neighborhood densities to preserve both efficiency and accuracy. Second, we propose del-consistency, a consistency model for ANNS caches that applies deletions eagerly and insertions lazily. Under this model, Aker implements a low-overhead refresh mechanism that bounds cache staleness and preserves high search accuracy. We integrate Aker into pgvector and evaluate it on representative workloads. Aker improves recall by up to 64 percentage points over prior solutions and increases QPS by up to 3.2x, while using 0.6x the memory of pgvector's shared buffers.

cs.DB↗
arXiv2026

Notices on a new functional identity and allied series transformations

In this paper, we establish an elementary functional identity \begin{align*}\sum_{k=1}^{n}\bigg(\frac{f(a,d_k)}{f(a,x)}\bigg)^{n-1}\prod_{i=1,i \neq k}^{n} \frac{g(x,d_i)}{g(d_k,d_i)}=1\end{align*} based on a pair of functions $f(x, y)$ and $g(x,y)$ satisfying $$f(x, a) g(b, c)+f(x, b) g(c, a)+f(x, c) g(a, b)=0.$$ The latter may serve as a prototype for the classical Weierstrass theta identity. As a direct application, we establish a general transformation formula for finite sums. Some special algebraic, triangular and elliptic series transformations are also presented.

math.CA↗
arXiv2026

Exact All-Level Positivity of the Bosonic Veneziano Amplitude

Tree-level partial-wave unitarity of the open bosonic Veneziano amplitude follows indirectly from the no-ghost theorem, but a direct proof from the beta function has been missing at the critical dimension. We prove nonnegativity at every mass level and spin throughout the sharp range 3 < D <= 26, using a Bessel recurrence that reduces the infinite sign problem to a manifestly positive bulk and a finite exact boundary.

hep-th↗
arXiv2026

Learning Where and What to Lift for Bi-planar X-ray-to-CT Reconstruction

X-ray imaging can be approximately modeled as the projection of an underlying volumetric attenuation field, with each measurement recording the accumulated attenuation along a corresponding ray path. Reconstructing a CT volume from only a few X-ray views is therefore severely ill-posed, as the projections collapse depth information and leave 3D locations of anatomical regions and their corresponding intensity distributions highly entangled and ambiguous. We observe that once the spatial organization of anatomical regions is established, estimating their CT intensities becomes substantially more tractable. Motivated by this, we propose LiftXR, an interleaved, geometry-guided framework that explicitly incorporates spatial layout recovery into CT reconstruction. Specifically, a layout lifter first generates a 3D anatomical layout from bi-planar X-rays, providing spatial guidance for an intensity renderer to reconstruct a CT volume. An anatomical parser then performs volumetric perception on the reconstruction, exploiting its spatially resolved boundary and intensity cues to recover a refined anatomical layout. This transition from projection-conditioned layout generation to reconstruction-conditioned anatomical perception allows the parsed layout to provide feedback for region-specific intensity calibration. Extensive experiments on two public datasets demonstrate that LiftXR consistently outperforms recent X-ray-to-CT reconstruction methods, establishing a new state of the art. Moreover, the reconstructed CT achieves superior performance in external downstream segmentation, indicating improved anatomical fidelity. Code will be released.

cs.CV↗
arXiv2026

Adaptive Protection for Evolutionary Feature Construction in Symbolic Regression with Application to Credit Classification

Evolutionary feature construction has shown strong promise in symbolic regression by automatically discovering informative transformations of input features that enhance a simple base learner. However, existing approaches often lack explicit mechanisms to preserve important constructed features discovered during evolution, and valuable genetic material can be lost when genetic operators disrupt effective features. This paper introduces an adaptive protection mechanism that leverages feature importance metrics to selectively preserve constructed features during evolution. The mechanism provides stronger protection for more important constructed features while still allowing less important features to be modified and to incorporate useful building blocks from more important features. We evaluate the approach using multiple feature importance calculation methods and demonstrate its robustness across different base learners. Experimental results on 98 regression benchmark datasets show that the proposed mechanism consistently improves solution quality over baseline approaches, and experiments on two credit classification datasets demonstrate that the method also extends effectively to improve search effectiveness beyond symbolic regression.

cs.LG↗
arXiv2026

MESA:Task-Adaptive Multi-Structure Evidence Selection for Long-Horizon Agent Memory

Long-horizon agents accumulate trajectories spanning hundreds of interleaved reasoning, action, and observation steps, where answering a query may depend on evidence buried far back in the history. External memory stores such trajectories as structured representations, yet each structure provides a distinct and incomplete view. Existing multi-memory systems either read a fixed set of structures for every query, inflating context and introducing noise, or route each query to a single structure, preventing the composition of complementary evidence. A controlled analysis on AMA-Bench shows that the optimal memory configuration is typically neither a single structure nor the full union, but a tailored composition of multiple structural memories that varies with query and task demands. Motivated by these findings, we formulate structure-level dynamic selection: selecting and fusing a query-adaptive subset from a library of specialized memory structures. We propose MESA (a Multi-structure Evidence Selection framework for long-horizon Agent), which builds five complementary structure views of each trajectory and learns from end-to-end answer-level feedback to select and fuse a query-specific subset for a frozen answer model. To learn under this weak supervision, MESA employs harness optimization with prior-guided search and UCB-guided scheduling to balance exploration and exploitation. On AMA-Bench, MESA outperforms the strongest baseline by 8.5% while using 41% fewer evidence tokens than the all-structure alternative.

cs.AI↗
arXiv2026

SkillHEX: Improving Agent Skills via Hypothesis-Driven Autonomous Exploration and Exploitation

Although agent skills equip LLMs with reusable procedural knowledge, manual maintenance suffers from high costs, unscalability, and misalignment. Real-world deployments thus require autonomous, on-demand skill evolution at test time, constrained by limited interaction budgets and a lack of training or validation sets. This setting introduces a severe sparse reward challenge, where outcomes conflate multiple latent failure causes. Under such ambiguity, existing methods that greedily refine a single incumbent skill are particularly vulnerable to an exploitation trap, allowing early misdiagnoses to exhaust limited trials along unproductive trajectories. To address this, we introduce SkillHEX, a closed-loop framework coupling hypothesis-driven self-verification with evidence-guided tree search. SkillHEX translates falsifiable failure hypotheses into executable tests, producing diagnostic evidence as dense reward without additional environment attempts. This evidence guides a search over persistent skill-revision branches, dynamically balancing the exploitation of supported edits with the exploration of plausible alternatives. Evaluated on 87 tasks from SkillsBench, SkillHEX outperforms existing self-evolving methods and achieves an average pass rate of 55.9% and 57.9% using GPT-5.3-Codex and Claude Opus 4.7 under a five-iteration budget, respectively.

cs.AI↗
arXiv2026

Observation of metastable chiral domain walls in a topological magnet

The interplay between topology and correlation can give rise to exotic collective excitations. The integer and fractional quantum anomalous Hall (QAH) magnets recently discovered in two-dimensional (2D) flatband systems are predicted to host spin excitations distinct from those in conventional magnets. Experimentally, nevertheless, these new excitations remain largely unexplored. Here we investigate spin-valley excitations in a twisted MoTe2 moiré superlattice using resonant ultrafast pump-probe spectroscopy. We observe a metastable spin-valley excitation in the QAH magnet below T ~ 3.7 K that survives reverse magnetic field several times larger than the saturation field. The behavior of this excitation is sharply distinct from ordinary domain walls and magnons, indicating a new type of spin-valley textures unique to topological magnets. We propose that these textures are chiral domain walls with an in-plane winding of the pseudospin order parameter along the domain wall. Their metastability arises from the interplay between the topological winding in real space and the quantum geometry of the parent bands in momentum space through a universal mechanism. These chiral domain walls govern the nonequilibrium dynamics of QAH magnets and may play a central role in their stability. Our study highlights intrinsic quantum geometry effects on spin excitations in topological magnets; and provides key insights into the fundamental mechanism limiting stability of topological protection.

cond-mat.mes-hall↗