Searcharxiv⌕ Search

arXiv subjects

Yiran Chen

Publications and source records attributed to Yiran Chen.

At least 19 recordsLinked to original sources
arXiv2026

Query-Conditioned Evidential Keyframe Sampling for MLLM-Based Long-Form Video Understanding

Multimodal Large Language Models (MLLMs) have shown strong performance on video question answering, but their application to long-form videos is constrained by limited context length and computational cost, making keyframe sampling essential. Existing approaches typically rely on semantic relevance or reinforcement learning, which either fail to capture evidential clues or suffer from inefficient combinatorial optimization. In this work, we propose an evidence-driven keyframe sampling framework motivated by an information-theoretic perspective. We consider maximizing the conditional mutual information between the selected frames and the answer given the query as an idealized objective, and use a modular singleton-gain surrogate to motivate a tractable frame-wise selection criterion. Guided by this motivation, we train a query-conditioned evidence scoring network using annotated answer-supporting segments. A contrastive objective encourages greater aggregate score mass on frames from evidence regions than on background frames, providing a practical evidence-based criterion beyond semantic similarity. Experiments on long-form video understanding benchmarks show that our method consistently outperforms prior sampling strategies under comparable frame budgets. With Qwen2.5-VL-7B under the same 32-frame budget, our method improves over uniform sampling by 10.1 points on LVBench and 4.4 points on the long-video subset of VideoMME.

cs.CV↗
arXiv2026

When No Answer Is Correct: Diagnosing Absent Answer Detection for MLLMs in Video Understanding

Multimodal large language models (MLLMs) have made substantial advancements in video understanding, yet the reliability of their responses remains underexplored. This work presents a diagnostic study of absent answer detection for MLLMs in video understanding, where the correct answer is deliberately excluded from the candidate set and a reliable model is expected to recognize that no valid option exists. We evaluate the absent answer detection behavior under three settings: multiple-choice questions augmented with a ``None of the Above'' option, open-ended generation with a detection instruction, and standard evaluation without any guidance. Across a diverse set of models and benchmarks, we find that MLLMs overwhelmingly select plausible distractors rather than detecting the absent answer. This failure is more pronounced in temporal reasoning tasks and worsens with denser frame sampling. We further explore chain-of-thought prompting as a mitigation strategy and find that while it substantially improves detection rates, performance remains unsatisfactory, suggesting that prompting-based strategies alone are insufficient to fully address this limitation. These findings expose a systematic failure in absent answer detection and highlight the need for explicit detection mechanisms in multimodal systems.

cs.AI↗
arXiv2026

BasisKV: Value Latents for Communication and Key Routing

Long-context large language model (LLM) inference is increasingly constrained by the cost of maintaining an ever-growing KV-cache. Low-rank K/V projections provide a promising way to compress the KV-cache with minimal quality loss, but prior work has largely optimized KV-cache compression in isolation, leaving distributed inference, especially with tensor parallelism where attention computation is partitioned across multiple GPUs, largely underexplored. We make two observations: (i) tensor-parallel communication is an important cost when deploying low-rank KV-cache compression in distributed inference; and (ii) Value compression can be associated with the output projection, allowing the same low-rank Value representation to reduce both Value-cache width and tensor-parallel communication. Based on these observations, we propose BasisKV, a low-rank KV-cache compression method for communication-intensive, long-context LLM inference. BasisKV jointly optimizes the low-rank factors across per-GPU attention partitions against the complete attention output, rather than fitting each partition in isolation. The compressed Value cache is further reused to help identify which Key pages should be accessed: it predicts part of the Key information needed for routing, while a Key-specific residual stores what cannot be recovered from Value. The original Keys are then retrieved only for the selected pages to compute exact QK scores. Across multiple LLM families and system settings, BasisKV achieves a better quality--efficiency tradeoff than existing low-rank baselines, reaching up to 1.42x end-to-end speedup under 8-GPU tensor-parallel inference. Our code is available at https://github.com/alexz949/BasisKV

cs.AI↗
arXiv2026

MoBiQuant: Mixture-of-Bits Quantization for Token-Adaptive Any-Precision LLM

Dynamic runtime latency and memory constraints necessitate flexible large language model (LLM) deployment, where an LLM can be inferred with various quantization precisions based on available computational resources. Recent work on such any-precision quantization either relies on hardware-inefficient vector quantization or induces additional scaling factors when switching between bit-widths. Meanwhile, existing post-training quantization (PTQ) methods calibrated for a fixed low precision show poor generalizability under runtime precision change. In this work, we attribute the source of poor generalization across bit-widths to a precision-dependent outlier migration phenomenon where the distribution of PTQ-sensitive tokens changes across precisions. Motivated by this observation, we propose MoBiQuant, a novel any-precision Mixture-of-Bits quantization framework that adjusts weight precision for flexible LLM inference based on token sensitivity. Specifically, we propose a many-in-one recursive residual quantization that can iteratively reconstruct higher-precision weights at runtime and mitigates outlier migration with a token-aware router to dynamically select the optimal inference precision of each token.Extensive experiments show that MoBiQuant matches or surpasses frontier single-precision PTQ while exhibiting strong elasticity, achieving significant memory savings and throughput gains of up to $1.34\times$ over state-of-the-art any-precision methods. Our code is available at https://github.com/SimWangArizona/MoBiQuant.

cs.LG↗
arXiv2026

InteractiveWorld: A Verifiable Human-Centric Environment for Building Better Interactive MLLM Assistants

People have long dreamed of an assistant that is always there to guide them and remind what they forget, from new dishes to lost keys. Powered by multimodal large language models (MLLMs), egocentric AI assistants on wearable devices are bringing this dream within reach: they see what the user sees and give instructions for user's physical work when necessary. However, testing such assistance is challenging and usually requires real people. The expensive and rare real interaction data leaves a key question unanswered: Can today's MLLMs truly help people in physical world? To answer this question, we propose InteractiveWorld, the first verifiable environment for closed-loop interaction between human and AI assistant. Unlike existing robot-centric simulators, InteractiveWorld lets the assistant guide a human agent who observes the scene, understands instructions, and acts independently. It thus realistically simulates how AI assistant collaborates with human: the assistant instructs, the human acts, and the environment executes actions and updates what they see next. Building on it, we introduce InteractiveBench, the first dynamic benchmark for egocentric AI assistants, with 120 multi-turn tasks across six categories. In each task, the assistant guides the human in real time, and every instruction shapes the outcome, which is scored by verifiable, state-based rewards. Experiments with 12 frontier MLLMs show they are still far from reliable assistants. Even the strongest model, Claude Fable 5.1, achieves at most 20% and 25% on long-horizon Guidance and Planning tasks, respectively. Overall, our work offers a verifiable platform and a rigorous evaluation set, laying a solid foundation for research on interactive MLLM assistants that truly help people in the physical world.

cs.HC↗
arXiv2026

SRE: Accelerating Zero-Knowledge Proofs via Scalar Redundancy Elimination in Multi-Scalar Multiplication

Multi-Scalar Multiplication (MSM) is a fundamental cryptographic operation used in Elliptic Curve Cryptography (ECC) across a wide range of applications. Its computation involves intensive elliptic curve point additions (PADD). MSM plays a critical role in cryptographic primitives such as polynomial commitments and zero-knowledge proofs (ZKPs), where it often becomes the runtime bottleneck. Consequently, optimizing MSM is an active area of research focused on reducing computational complexity and accelerating performance. The current state-of-the-art algorithm for large-scale MSM is Pippenger's bucket method, which consists of three main steps: point merging, bucket aggregation, and window aggregation. Among these, the point merging step is the primary performance bottleneck. Our work targets this major computational bottleneck. To reduce operations for practical applications, we propose a novel Scalar Redundancy Elimination (SRE) algorithm with three approaches: a vanilla array-based approach, a list-based greedy approach, and a list-based exhaustive approach, all incorporating an early stopping technique. Depending on the use case, these strategies can be integrated into our modified MSM algorithm, which is based on Pippenger's bucket method. As a result, our proposed MSM algorithm, enhanced with the SRE technique, incurs less than $3\%$ additional search time, while reducing the number of operations by $25\%$, leading to a $30\%$ speedup in runtime compared to the standard Pippenger's bucket method. This translates to a $10 \sim 20\%$ runtime reduction in various ZKP systems that rely heavily on MSM.

cs.CR↗
arXiv2026

ZKPU: Zero-Knowledge Processing Unit for Heterogeneous Workloads

Zero-knowledge proofs (ZKPs) have become a fundamental building block for privacy-preserving computation, blockchain systems, and verifiable machine learning. Modern ZKP protocols span two distinct families: curve-based protocols, which rely on large finite-field arithmetic, and hash-based protocols, which operate over native 64-bit fields. Existing hardware accelerators are specialized for one protocol family because they are built on operand-scanning Montgomery multiplication, resulting in fixed-width datapaths, poor utilization across heterogeneous operand widths, and limited scalability. This paper presents \emph{ZKPU}, a Zero-Knowledge Processing Unit for heterogeneous ZKP workloads. ZKPU introduces a new compute paradigm by co-designing finely integrated product scanning (FIPS) Montgomery multiplication with a reconfigurable Twin Systolic Fabric (TSF), enabling modular multiplication at arbitrary widths in 64-bit increments. Combined with a fine-grained Deque buffer, on-chip twiddle-factor generator, and memory-efficient MSM preprocessing strategy, ZKPU provides a unified architecture for both curve-based and hash-based protocols. Evaluation using Groth16 and Plonky2 shows that ZKPU achieves up to $144\times$ speedup for NTT, $13.6\times$ for MSM, and approximately $7.2\times$ end-to-end application speedup over state-of-the-art accelerators, while being the first architecture to efficiently support both protocol families on a single reconfigurable hardware platform.

cs.AR↗
arXiv2026

Steering Vision-Language Models for Visual-Contextual Privacy in Location Disclosure

Vision-language models (VLMs) can infer sensitive information such as geolocation from subtle visual cues, creating privacy risks when responses disclose more detail than the visual context warrants. We study visual-contextual privacy in geolocation disclosure, where a VLM should reveal location information only at the granularity appropriate to the visual context depicted in the image. We first show that this contextually appropriate granularity is recoverable from pre-generation hidden states, even when generated responses are misaligned, with disclosure levels exhibiting an ordered structure along a common hidden-state direction. Motivated by this, we propose an inference-time route-and-steer framework: an ordinal granularity router maps visual-contextual privacy representations to a disclosure route, and a disclosure-level-conditioned steering module applies route-specific hidden-state interventions during decoding. Across four VLM backbones, our method improves visual-context-aware disclosure alignment, better balances over- and under-disclosure, and incurs only modest changes on general capability benchmarks. It further transfers to another dataset with a distinct data distribution and privacy-risk taxonomy.

cs.CV↗
arXiv2026

Sensitivity or Criterion? Measuring and Moving When Language Models Act

Before an agent acts, it must decide whether action is warranted. A single accuracy cannot distinguish failure to recognize a warranted action from reluctance to act. Signal-detection theory separates sensitivity from criterion, but criteria estimated from authored binary labels depend on each benchmark's example mix. We introduce FlipAct, a diagnostic of tool use in physical states. A rule over annotated tool properties computes each answer and a graded evidence score, fixing the Yes/No boundary at zero across models. Questions form 2-by-2 quads that hold required knowledge fixed while the state flips. The slope of the fitted Yes-rate curve measures sensitivity; its crossing at one half measures criterion. Across 44 open models, sensitivity rises with size within a family, and its ranking agrees with three of four external when-to-act benchmarks. Models respond to evidence sign rather than magnitude, accepting actions that leave the state no better about as often as helpful ones. When Yes means act, most models are conservative across rephrasings; in some, this partly reflects a preference for No. Criterion is not determined by size. Activation steering shifts criterion with weights fixed; distillation from a model's own steered copy puts the shift into its weights without a significant sensitivity change. The distilled shift transfers to six external benchmarks, including two without Yes/No answers, while criterion-free AUC is preserved on the five benchmarks where it is available. Accuracy improves where models start conservative and declines or remains within error where they start permissive. Project page: https://sixundong.com/projects/flipact

cs.CL↗
arXiv2026

Gamma: Grounded Multi-Agent Memory with Mechanical Audit for Memory-Intensive Manipulation

Pretrained vision-language-action (VLA) policies fail on memory tasks, behaviour that depends on events observed long before the current frame, because their training data is overwhelmingly Markov and mapping episodic memory directly to action chunks is hard. Yet the same policy, finetuned once to follow a privileged oracle's grounded-subgoal text, nearly solves these tasks: the difficulty lies entirely in mapping memory to a grounded symbolic subgoal. Existing work entrusts this stage to a single VLM that selects keyframes and reasons over raw frames, and falls far short of the oracle: key identities and dynamics are buried in noisy pixels, the reasoning spans hundreds of frames in an unbounded context, and hallucination corrupts the memory itself. We instead present GAMMA (Grounded multi-Agent Memory with Mechanical Audit), which builds the stage as a collaborating two-agent memory system: a detector tool (SAM-3) for spatial grounding, a VLM writer that distils each replan window into one grounded text line, an append-only text memory bank, and a VLM reasoner that reads the bank and emits the next grounded subgoal at the oracle's cadence, wrapped in a propose-verify harness that admits, defers, corrects, or rejects every agent claim against mechanical visual evidence, at training-corpus construction and at deployment alike. On a sixteen-task memory-manipulation suite GAMMA recovers a large fraction of the oracle ceiling with the policy held fixed, reaching the ceiling on several tasks, and transfers with unchanged contracts to a second benchmark.

cs.RO↗
arXiv2026

Stable Scores, Unstable Answers: Frame Phase and Option Order in Video Multiple-Choice Evaluation

Video-language models are ranked by multiple-choice accuracy on frames from a uniform grid. The grid has two parameters, a rate and a phase, and benchmarks report only the rate. The phase moves answers: two deployed samplers differing only by a half-step phase offset answer 23.6% of questions differently while scoring within a point, and across four releases from two families shifting only the phase changes roughly one answer in five after controlling option order. PHASEFUSION decodes three offset grids and averages the option posteriors. The grids are the polyphase components of the dense grid. Fusion matches a 32-frame single pass in accuracy within a prespecified margin (logit-scored) and cuts the answers a half-step shift of all three grids changes from 18.2% to 10.1%. Option order, which changes only the presentation, is flagged instead by a one-pass answer margin. Report the phase convention with the budget, or marginalize it.

cs.CV↗
arXiv2026

Knowing When to Trust a Prior: Reliability-Gated Cue Fusion for Video Gaze Prediction

Video gaze prediction is led by gaze-trained models, yet gaze-free priors carry signal those models have not absorbed, if one knows when to trust them. We propose FocusGate, a gated ensemble of gaze-free priors whose members may abstain. A per-frame gate reads three shape statistics of a defocus map and selects the frames on which the estimator is above chance on average, so rejected frames reduce to the base exactly, while midrank normalisation lets an all-zero prior abstain at zero parameters. Gated fusion is significantly positive on film, sports and web video, whereas unconditional fusion is harmful on sports and null on web. Added to four supervised predictors, the NTIRE 2026 champion among them, FocusGate improves all sixteen model-domain cells in shuffled AUC, fifteen significantly, one domain pre-registered and scored once, while adding only 1% to the champion's latency. Alone, it surpasses TASED-Net and UNISAL in shuffled AUC on film with a 16-frame causal mean.

cs.CV↗
arXiv2026

Coupled but Late: Turn-Taking Between Full-Duplex Speech Models in Unscripted Dialogue

Full-duplex speech models are trained to converse with a person, but they are increasingly made to converse with each other, in self-play data generation, agent societies, and model-based evaluation. In that loop no human absorbs a timing error: each model's turn-taking is the other's input. We ask what timing the loop settles into. Two PersonaPlex-7B instances exchange audio tokens on a shared clock in unscripted conversation, and one floor-transfer rule is applied to them and to Switchboard. Their timing is coupled: re-pairing speakers across conversations destroys it. But the floor changes hands late, at a median of 400-560 ms against 137 ms for humans, and the last 120 ms of the partner's turn, where human projection places a tenth of its transfers, holds 1% of theirs. Delaying one direction of the channel shifts the response one-for-one and leaves the run-up to it empty, consistent with a reactive wait after the perceived end rather than the turn-end projection human timing requires.

cs.AI↗
arXiv2026

A Shape-Adaptive Architecture with Disaggregated Quantization for Efficient LLM Serving

Large language models (LLMs) have become the backbone of modern AI applications, but pose significant challenges for efficient inference. Their autoregressive generation divides execution into two phases: prefill, dominated by large GEMMs, and decoding, dominated by small GEMVs. Modern serving systems further introduce complexity through continuous batching and prefill-decoding disaggregation, leading to dynamic workloads and phase separation. However, existing accelerators remain poorly aligned with these system-level behaviors, resulting in inefficiencies in LLM serving. In this work, we present DynaCore, a unified architecture for efficient LLM serving via system-architecture co-design. We observe that the compute tile a systolic array executes, its Minimum Efficient Unit (MEU), spans all three GEMM dimensions. DynaCore reshapes the MEU along all three: spatially it trades array width against height asymmetrically, raising weight delivery while leaving the input path untouched, and temporally Split-K maps the reduction onto the array, folding partial sums through the interconnect the array already has. To exploit phase separation, we further propose disaggregated quantization, applying dual-side quantization to prefill and weight-only quantization to decoding, with an inner-product mixed-precision datapath that keeps output width invariant to precision. A runtime scheduling framework then selects an MEU per batch. Evaluation with real-world serving traces shows that DynaCore substantially reduces service-level latency over quantization and reconfigurable accelerators, improving TTFT by 3.50x and 2.97x and TPOT by 36.55x and 8.02x, respectively.

cs.AR↗
arXiv2026

MARS: Multi-resolution Adaptive Routing for Sequential Recommendation

Long-history recommenders often compress each user's history into a compact, candidate-independent memory that is cached and reused to score large candidate pools. We show that real user histories exhibit multi-scale semantic structure, with short-lived intent, medium-term interests, and long-term preferences coexisting in one sequence, and that monolithic cached memories preserve these scales unevenly: linear probes recover recent and mid-range content far worse than long-range content. We call this failure mode \textit{temporal aliasing}. We propose \textbf{MARS}, a multi-resolution user memory that writes the full history into recurrent state tracks anchored to different half-lives, and a sparse routing reader that materializes compact seed memories by selecting the relevant temporal resolutions for each seed, preserving fixed-size candidate scoring. MARS outperforms strong baselines on three public datasets, with gains that grow with history length. Component-matched ablations with paired tests show that temporal diversity and selective routing each contribute beyond what hard-window memories or added capacity provide. The advantage of MARS over its interface-matched baseline also widens after within-user behavioral shifts, at about $1.02\times$ that baseline's warm-cache serving latency for $1{,}000$ candidates per user.

cs.AI↗
arXiv2026

The Functional Structure of Post-Compression Recovery in Low-Rank LLMs

Different low-rank compression methods can produce compressed LLMs that respond differently to the same post-compression recovery procedure, and relative advantages observed between methods at the compression endpoint may shrink, grow, or even reverse after recovery. We ask whether this recovery heterogeneity reflects functional structure beyond scalar loss evolution, and how that structure evolves throughout recovery. Our results establish that this heterogeneity reflects a reproducible compression-induced functional structure, which we formalize as recovery pressure. To characterize this structure consistently throughout recovery, we develop a standardized functional characterization within each backbone that is applicable across heterogeneous low-rank methods. The primary backward characterization reveals reproducible module-wise structure across independent probes, while a complementary forward-only characterization recovers related structure without loss or backpropagation. We further find that recovery pressure measured at the endpoint is associated with subsequent recovery response; during recovery, its module-wise structure is reorganized non-uniformly, and localized updates induce distributed responses beyond directly updated modules. Further evidence indicates that tracking this evolving structure provides a complementary functional view of recovery progress alongside scalar loss.

cs.AI↗
arXiv2026

Preserving Mathematical Reasoning in Compressed Diffusion Language Models via Trajectory-Aware Low-Rank Approximation

Diffusion language model (dLLM) compression faces a known challenge because calibration is typically performed on clean, fully visible activations, whereas inference traverses partially masked intermediate states. For low-rank compression, this raises two questions. First, can low-rank optimality still be characterized when approximation quality is measured over trajectory-distributed states, and second, does the choice of calibration states affect mathematical reasoning preservation under compression? We address these questions by formulating a trajectory-aware low-rank objective over corruption levels and masking realizations. To estimate this objective efficiently, we propose Traj-MC, which estimates the trajectory second moment through Monte Carlo sampling and yields exact sampled-state optimality and population consistency. Under matched compression budgets, trajectory-aware calibration improves reconstruction over the generation trajectory and preserves substantially more mathematical reasoning than clean calibration on mathematical reasoning benchmarks. Our results connect trajectory-aware low-rank optimality to the reasoning capability retained after dLLM compression. Our code is available at: https://github.com/Zishan-Shao/traj-mc.git.

cs.AI↗
arXiv2026

Joint Branch-Space Transform Coding for Diffusion Activation Quantization with Classifier-Free Guidance

Post-training quantization for diffusion models increasingly exploits timestep, feature, and layer structure. While recent work has begun incorporating CFG structure into diffusion quantization, activation quantization still operates independently across conditional and unconditional coordinates, leaving cross-activation structure unexploited. We show that matched CFG activations form a strongly correlated two-dimensional source and that, under a fixed bit budget, the choice of branch coding basis materially affects quantization fidelity. Motivated by this observation, we introduce branch-space transform coding, which rotates matched CFG branches via an offline derived 2x2 orthogonal matrix, requiring minimal modifications to model parameters or the quantization pipeline. We further derive the Guidance-Correlation Branch Transform (GCBT), which jointly incorporates the CFG guidance direction and cross-branch second moments. Under an equal-rate quantization-noise surrogate, GCBT admits a closed-form per-layer solution without gradient optimization or angle search. Applied on top of existing diffusion PTQ methods, GCBT yields statistically significant fidelity gains in most evaluated comparisons with no statistically significant degradation, while leaving the underlying host quantization pipeline unchanged.

cs.CV↗