Searcharxiv⌕ Search

arXiv subjects

Ke Yang

Publications and source records attributed to Ke Yang.

At least 19 recordsLinked to original sources
arXiv2026

Perception-Augmented Databases for Effective Visual Analytics

Analysts often use sampling in visual exploration to overcome the computational and perceptual bottlenecks of working with massive datasets. Yet, existing sampling methods optimize for statistical or geometric data properties, without explicit consideration for how humans perceive a visualization. We propose perception-augmented databases: a database framework that stores perceptual models of data as precomputed metadata and exposes a new query operator---perception-aware sampling---that selects subsets optimized for how humans visually perceive the result. We make the following contributions: (1) We introduce perception-augmented databases and design PAwS, a perception-aware sampling operator for scatterplot visualizations that leverages saliency maps---a computer vision tool for predicting areas of visual attention---combined with density and coverage objectives. (2) We design ApproPAwS: a fast approximate visualization method that works directly over a perception-aware compressed synopsis of the data, achieving up to 100x speed-ups with minimal loss in visual fidelity, and without accessing the underlying data at query time. (3) We contribute a perceptual similarity metric that evaluates the quality of a sample by comparing its saliency map to that of the original dataset, a novel evaluation methodology, applicable to any sampling method for scatterplots. (4) Our extensive experimental evaluation over datasets up to 3.5M points demonstrates that our methods consistently outperform five state-of-the-art sampling algorithms. A user study confirms that PAwS samples are preferred by humans, validating our quantitative findings.

cs.HC↗
arXiv2026

GenDSR: Transferring Representations from Video Generation Models for Dynamic Spatial Reasoning

Dynamic spatial reasoning is essential for connecting visual intelligence to thephysical world, yet remains challenging for vision-language models (VLMs), which must preserve scene state while tracking how spatial relations evolve over time. Meanwhile, video generation models (VGMs), trained to synthesize temporally coherent world dynamics, offer a rich source of spatiotemporal representations. We present GenDSR, a framework that transfers intermediate representations from VGM into VLM for dynamic spatial reasoning. Rather than treating a VGM feature as a monolithic prior, GenDSR constructs two complementary branches: a raw branch preserving holistic generative context and a delta branch emphasizing temporal variation. Task-conditioned tokenwise gates then fuse both signals and inject the result into the native visual representation. On DSR-Bench, GenDSR achieves 67.2%, surpassing the previous best result and establishing a new state of the art.

cs.CV↗
arXiv2026

Memory Tax: Dissecting the Net Value of Agent Memory

Memory is increasingly used in long-horizon agents, yet the net value of building memory over direct retrieval from raw history remains largely unclear. Through a large-scale evaluation across multiple benchmarks and model backbones, we find many dedicated memory systems underperform naive RAG in many cases, indicating a negative net value. Taking RAG as a reference, we dissect the net value of memory into the gains and losses over direct retrieval, termed memory benefit and memory tax. These gains and losses arise because memory process changes how the raw information is organized and accessed. We view such changes as the double-edged deviations from the raw history. They are originally designed and introduced to benefit the task, for example by reorganizing facts or distilling preferences, but some may also remove or obscure evidence, giving rise to memory tax. Since memory benefit reflects the expected gains of its design, we then focus more on the overlooked memory tax, study how it arises from the system and evaluation side, and generalize the concept to more application scenarios of memory. We hope the notion of memory tax can provide a new lens and shift more attention from standalone performance to the net value of memory, informing more reliable memory designs and evaluations. We will open-source the code and results to the community. Project Page: https://hexuan21.github.io/MemoryTax/

cs.CL↗
arXiv2026

Extraction of transverse-momentum-dependent helicity distributions of the nucleon

We present an updated global analysis of the transverse-momentum-dependent (TMD) helicity distributions of the nucleon from measurements of the longitudinal double-spin asymmetry $A_{LL}$ in semi-inclusive deep-inelastic scattering (SIDIS). The analysis incorporates target- and detected-hadron-mass corrections, next-to-next-to-leading-order matching in the small-$b_T$ operator product expansion, and an improved treatment of correlated systematic uncertainties. The present data constrain the up- and down-quark helicity TMDs, whereas the sea-quark and gluon distributions remain weakly constrained. After integration over transverse momenta up to the hard scale, the up- and down-quark distributions agree with collinear helicity distributions within uncertainties. Using the extracted TMDs and the Wandzura-Wilczek-type approximation, we predict the $\cosϕ_h$ modulation of $A_{LL}$ and find agreement with the HERMES and CLAS measurements. We also provide predictions for SIDIS $A_{LL}$ at CLAS12 and for longitudinal single-spin asymmetries in $W^\pm$ production with leptonic decays at STAR kinematics. An impact study with pseudodata for the proposed Electron-Ion Collider in China (EicC) indicates substantial potential to improve constraints on helicity TMDs at intermediate $x$, including the presently weakly constrained sea-quark sector.

hep-ph↗
arXiv2026

Learning to Program Retrievals: Composing Search Primitives via Reinforcement Learning

Retrieval-augmented language models increasingly use multi-step search to solve knowledge-intensive tasks, yet existing systems typically expose retrieval through fixed pipelines or collections of atomic tools. We introduce Retrieval Program Learning (RPL), a programmable search framework that allows a policy to compose search primitives into executable programs with local state and control flow. This enables adaptive search that can retrieve broadly, process intermediate results, and selectively construct model context without tying retrieval breadth to context consumption. However, the resulting flexibility creates a difficult exploration problem: useful programs may require several coordinated decisions, while reinforcement learning often supplies only sparse feedback. To address this challenge, we propose program mutation, a grammar-constrained and execution-verified procedure that generates local variants of suboptimal programs sampled during RL, converts them into training trajectories, and distills them back into the policy. We evaluate RPL on open-domain question answering and corpus-level reasoning tasks, comparing it with a range of retrieval and reasoning baselines. RPL consistently improves open-domain QA performance across model sizes and in- and out-of-domain benchmarks, with particularly large gains on multi-hop tasks. Notably, a 4B model trained with RPL outperforms all 8B model baselines. On corpus-level reasoning, RPL achieves the highest answer F1 and document-coverage F1 for both model sizes while substantially reducing context consumption and retrieval turns. Our results show that programmable search expands the retrieval strategies that agents can learn, while program mutation provides an effective mechanism for exploring useful program structures beyond direct on-policy sampling.

cs.CL↗
arXiv2026

Tokenized Joint Source-Network Coding for Loss-Resilient Video Streaming

For decades, conventional video streaming systems have relied on packet-level forward error correction (FEC) codes and retransmissions to ensure reliable video delivery. However, in real-time communications, FEC is inherently inefficient under unknown and time-varying packet-loss conditions, while retransmission can incur excessive latency and fail to meet stringent playout deadlines. Emerging deep joint source-channel coding (DeepJSCC) provides an alternative by learning channel-noise-resilient representations, yet its tight coupling with the physical layer makes it difficult to integrate into today's layered network architectures and protocols. In this paper, we propose TokJSNC, a simple-but-effective tokenized joint source-network coding paradigm for packet-loss-resilient video streaming. Rather than first compressing video into a compact bitstream and then protecting it with packet-level FEC, TokJSNC directly encodes video into variable-length discrete token-stream, whose transmission rate is jointly adapted to video content complexity and network conditions. By exploiting the spatiotemporal correlations among learned video tokens, TokJSNC enables robust video reconstruction over a wide range of packet-loss rates without explicit FEC or retransmissions. Consequently, TokJSNC brings the JSCC-like graceful degradation property to the network layer while remaining compatible with existing network architectures and transport protocols. Experimental results show that TokJSNC maintains an average playback frame rate above 22 fps even at a 70% packet-loss rate, whereas the best-performing baseline drops below 12 fps. Overall, TokJSNC establishes a practical pathway for repurposing modern generative video tokenizers for loss-resilient streaming, while providing a fundamental framework for video token communications.

eess.IV↗
arXiv2026

Exact black hole solutions in Palatini Kalb-Ramond gravity

We investigate static and spherically symmetric black holes in Palatini Kalb-Ramond gravity, where a nonzero vacuum expectation value of the Kalb-Ramond field spontaneously breaks local Lorentz symmetry. Treating the metric and the torsion-free affine connection as independent variables, we derive the modified field equations and obtain an exact family of solutions encompassing positive, vanishing, and negative values of the cosmological constant $Λ$. Unlike the corresponding purely metric formulation, the Palatini theory consistently allows both Lorentz-violating parameters $\ell_1$ and $\ell_2$ to be nonzero. Using the Iyer-Wald formalism, we determine the conserved mass of the black hole solutions. For the $Λ\leq0$ sector, we further verify the first law and the Smarr relation, identifying the conserved mass as the thermodynamic enthalpy. We then confront the $Λ=0$ solution with Mercury's perihelion precession, solar light deflection, and the Shapiro time delay. Once the central mass parameter is calibrated by planetary dynamics, these observables constrain the Lorentz-violating parameters only through $q\equiv\ell_2/(1-\ell_1)$. Among these tests, Mercury's perihelion precession yields the most stringent constraint, $-7.4\times10^{-12} \leq q \leq 3.7\times10^{-11}$.

gr-qc↗
arXiv2026

MoE-CORE: Coordinated Expert Offloading and Residency for Memory-Constrained MoE Inference

Sparse expert activation reduces MoE models' computation, yet expert weights can exceed limited device memory. Offloading makes inference feasible on a compact AI appliance but exposes host-to-device transfers to the inference path. We present MoE-CORE, a system that coordinates expert offloading and residency for memory-constrained MoE inference. It stages complete expert layers in alternating buffers during prefill. During decode, it combines nonuniform layer-wise cache capacity, domain-informed initialization, routing-history-aware replacement, and cross-layer prefetching. The main configuration executes router-selected experts exactly; an optional score-based substitution path handles eligible low-score misses. The main comparison uses 1K- and 128-token output caps for MoE-CORE and vLLM Prefetch, respectively. Across five workloads per model, MoE-CORE records a mean time per output token (TPOT) of 38.0-44.8 ms versus 1268.9-1269.1 ms for the evaluated vLLM Prefetch configuration on DeepSeek-V4-Flash-W4A8; the corresponding values on GLM-5.2-W4A8C8 are 206.6-220.5 and 5941.5-5941.8 ms. Under an 84-GB NPU-memory cap, the best measured DeepSeek GSM8K configuration achieves a TPOT of 21.5 ms with approximate expert substitution and multi-token prediction (MTP) at depth 2. These results support coordinated expert residency and transfer scheduling under a device-memory constraint. The code is here.

cs.DC↗
arXiv2026

ShallowStream: Index Shallow then Answer Deep for Streaming Video Understanding

Streaming video understanding is a critical capability for real-world applications, including embodied intelligence, autonomous driving, industrial monitoring, surveillance and early warning, and wearable assistants. However, processing continuous video streams with multimodal large language models (MLLMs) is computationally expensive. Existing efforts have explored reducing streaming overhead through visual token pruning, token merging, quantization, on-demand frame retrieval, and context offloading. However, most existing methods overlook the dimension of model depth. Repeatedly executing full-depth MLLM prefill over incoming frames is prohibitively expensive, incurring substantial computational overhead and causing the KV cache to grow at a rate directly proportional to the prefill depth. To address these challenges, we propose ShallowStream, a novel framework that leverages the shallow layers of an MLLM to simultaneously perform frame encoding and retrieval index building. During stream processing, ShallowStream maintains an always-on lightweight index using the KV cache of shallow layers. During query-time answering, we leverage the attention scores generated by the shallow layers to score context frames and employ a diversity-aware selection strategy to retrieve precise and comprehensive evidence. ShallowStream achieves performance on par with the strongest existing streaming methods, while reducing per-frame prefill latency and 10-second end-to-end latency by up to 52.1x and 11.9x, respectively. Our code is available at https://github.com/CURRENTF/ShallowStream.

cs.CV↗
arXiv2026

An absolute measure of heterogeneity for lnOR in meta-analysis

Quantifying the heterogeneity is an important issue in meta-analysis. The conventional heterogeneity statistic, $I^2$, heavily depends on study sample sizes and tends to approach one as the sample sizes increase. To overcome this limitation, a sample size independent measure, ${\rm ICC}_{\rm MA}$, has recently been developed to quantify the heterogeneity, yet this method is restricted to meta-analysis with continuous outcomes. In practice, however, binary outcomes are more widely encountered, with the log odds ratio (lnOR) frequently adopted as an effect size to compare the effects of two treatments in terms of odds. To fill the gap, we propose a new heterogeneity measure for meta-analysis with binary outcomes by introducing a latent continuous variable model. Under this framework, the proposed measure admits a closed-form expression within the random-effects meta-analysis model with lnOR as the effect size. We define this sample size independent measure as ${\rm ICC}_{\rm MA}^{\rm OR}$, and moreover propose a new estimator, $I^2_A$, to evaluate this measure. Simulation studies demonstrate that our new estimator is nearly unbiased and aligns closely with its counterpart applied for standardized mean differences when the continuous variable is observable. A real data application further demonstrates that the proposed heterogeneity statistic for binary outcomes and its counterpart for continuous outcomes provide interpretable and coherent estimates across different outcome types.

stat.ME↗
arXiv2026

MedProb: Probing Internal Representations of Vision-Language Models for Medical Question Answering

Medical visual question answering (Med-VQA) is often assumed to require medical fine-tuning, large models, or complex multi-agent pipelines. We revisit this assumption with \textbf{MedProb}, a lightweight probing framework that predicts multiple-choice Med-VQA answers from frozen VLM representations without free-text generation. Across PATH-VQA, SLAKE, and VQA-RAD, MedProb recovers substantially more answer-relevant signal than prompting and performs stronger than medical VLMs and agentic systems. Probing also reduces the apparent gap between small and large models compared to prompting, suggesting that smaller VLMs contain more recoverable Med-VQA signal than generation-based evaluation reveals. Across 14 matched general-purpose and medical VLM pairs, medical adaptation does not consistently improve this linear decodability. Finally, free-text generation exhibits an answer-position bias of up to 10 percentage points, whereas MedProb also has positional bias, however, it is impacted differently than prompting. Our main results target the multiple-choice/multiclass Med-VQA setting; we additionally show the probe can be extended to open-ended generation via a rejection-sampling scoring procedure.

cs.CL↗
arXiv2026

Medical Heuristic Learning: An LLM-Driven Framework for Interpretable and Auditable Clinical Decision Rules

Predictive modeling for clinical decision support requires both strong predictive performance and transparent, auditable, and human-reviewable decision logic. Although deep learning and tree-based ensemble methods can achieve high accuracy, their black-box nature remains a major obstacle to trustworthy clinical deployment. Moreover, clinical prediction often operates under practical constraints, including limited sample sizes, severe class imbalance, and feature evolution arising from changes in diagnostic criteria or clinical documentation practices. We propose Medical Heuristic Learning (MHL), a constrained paradigm for LLM-assisted rule learning. Rather than relying on updates to implicit model weights, MHL integrates statistical probes, medical knowledge probes, initial rule synthesis, and iterative rule optimization to construct an executable rule-based expert system. The resulting rule system is expressed entirely using the native logical and control-flow constructs of a programming language. Valid rule versions are recorded and retained along the search trajectory, making the decision logic explicit, interpretable, and auditable. MHL also supports continual learning by using previously validated rules as a starting point and iteratively revising them in response to updated feature information under data drift or feature evolution. MHL is not tied to any specific programming language. Comprehensive experiments on medical datasets show that MHL achieves predictive performance comparable to that of state-of-the-art methods, performs favorably in small-sample and highly imbalanced settings, and supports the transfer and adaptive revision of validated rules under feature evolution. Overall, these findings suggest that non-gradient-based heuristic systems offer an approach to balancing predictive performance and transparency in clinical decision support.

cs.AI↗
arXiv2026

StudentSim: Training LLM-based Student Simulators

AI tutors are most useful when they adapt to each student's strengths, weaknesses, and preferred guidance, but evidence about which guidance works for which student is sparse, slow, and costly to collect from real learners. Student simulators can provide this signal as a proxy, yet existing approaches are limited: state-tracking models fit student behavior but struggle to process explanations or corrections, while LLM role-play follows guidance fluently but does not reliably match the competence of the student being imitated. We present StudentSim, a training framework that turns sparse per-student data into individualized simulators through pooled training followed by per-student specialization. The resulting simulators both mirror a student's own responses and update them under tutor guidance. We also introduce StudentSimEval, a standardized protocol covering 60 students across chess, second-language English writing, and mathematics, using public learner datasets with de-identified records shared for research. StudentSimEval measures behavioral fidelity (F), or how well a simulator matches a student's responses, and guidance responsiveness (R), or how readily it updates under tutor guidance, with all methods fit and evaluated on the same records. Across all three domains, StudentSim outperforms GPT-5.4 on both metrics. In chess, StudentSim reaches F=0.51 and R=0.91, compared with 0.23 and 0.72 for GPT-5.4 and 0.45 and 0.27 for Maia2. As a proof of concept, using StudentSim as a reward model for tutor reinforcement learning produces a chess tutor that expert humans rate as more accurate, better-guided, and more personalized than a no-RL baseline and a tutor trained against a GPT-5.4 simulator reward. Code is available at https://github.com/microsoft/StudentSim.

cs.CL↗
arXiv2026

VGI-Bench: Probing Visual Intelligence in Video Generation Models

Recent studies suggest that video generation models can exhibit certain forms of zero-shot visual reasoning through generated frames. Yet reliable evaluation remains challenging: benchmarks should adopt inputs aligned with the visual priors of current video models, require valid evolving processes rather than only plausible final states, and calibrate task difficulty to remain challenging yet partly feasible. To this end, we introduce VGI-bench, containing 27 tasks and 810 instances, organized by a two-level taxonomy of task domains and skill tags for fine-grained evaluation of visual reasoning capabilities of video generation models. Our evaluations show that current generative systems can solve a subset of visually grounded reasoning tasks, but remain far from reliable, with even the strongest model, Seedance 2.0, achieving only 51.0% under our evaluation criteria. Our analysis further explore the output failure modes, input condition sensitivity, performance transfer boundary from synthetic fine-tuning, and internal denoising perspective revealing limited self-correction, where later steps mainly refine early hypotheses rather than correct reasoning errors. We hope VGI-bench will help stimulate the development of next-generation video generation models. Website: https://hexuan21.github.io/VGI-Bench/

cs.CV↗
arXiv2026

Robust and Efficient Feature Extraction for Spike Sorting via the Walsh-Hadamard Transform

Implantable neural interfaces require low-power real-time signal processing to remain within strict thermal and bandwidth constraints, motivating lightweight feature extraction methods for on-chip spike sorting. This work presents the Walsh-Hadamard Transform (WHT) as a hardware-efficient feature extraction method for neural spike classification. WHT can be implemented using only adders, subtractors, and registers without coefficient memory. WHT performance is compared against the Compressed Hadamard Transform (CHT) and Principal Component Analysis (PCA), improving mean F1-scores from 55-60% to 70-75% on difficult high-noise datasets and from 90-95% to 95-99% on all other simulated datasets. In addition to improved classification performance, WHT demonstrates greater robustness to noise, downsampling, reduced training size, and distance metric selection, maintaining standard deviations typically below 5%, while CHT and PCA reach up to 10% under high-noise conditions.

eess.SP↗
arXiv2026

Answer Presence Drives RAG Rewriting Gains

Retrieval-augmented QA pipelines often route retrieved passages through an LLM \emph{rewriter} before a smaller reader, lifting F1 by tens of points on multi-hop benchmarks; this gain is typically credited to improved evidence quality. We ask whether that lift is causally driven by the gold answer string appearing in the rewritten context rather than by curation per se, using a controlled intervention audit. For each rewritten context we re-run the reader after one of four controlled edits to the compile output: removing the gold answer span, replacing a length-matched random non-answer span (placebo), or injecting the gold into rewrites where it was absent (at the prefix or at a midpoint sentence boundary). Across twelve completed (cell, baseline) intervention runs spanning three reader families (Qwen2.5-7B, Qwen3.5-35B, GLM-4.7), two datasets (HotpotQA, 2WikiMultihopQA), and three compiler arrangements (MA-only, MB-only, MA$+$verify), removing the gold answer drops reader F1 by $28$ to $64$ points beyond the length-matched placebo on paired \texttt{answer-in-compile} strata, and prepending the gold into rewrites that lacked it raises F1 by $+0.7$ to $+9.7$ points in $10$ of $12$ (cell, baseline) combinations. A companion five-sentinel audit shows the conventional single-\texttt{[MASK]} probe is itself sentinel-fragile: on 2Wiki it reports a $+4.12$~F1 ``non-leakage residual'' that flips to $-3.33$ to $-7.81$~F1 under four alternative sentinels and fails an equivalence test for three of those four ($1/4$~pass). We do not propose a new rewriter or mitigation; we release the intervention runner and the sentinel panel so that other rewriter-gain claims can be tested against the same standard.

cs.AI↗
arXiv2026

The MiniMax-M2 Series: Mini Activations Unleashing Max Real-World Intelligence

We introduce the MiniMax-M2 series, a family of Mixture-of-Experts language models built around the principle that mini activations can unleash maximum real-world intelligence. The flagship M2 contains 229.9B total parameters with only 9.8B activated per token. Designed end-to-end for agentic deployment, the M2 series rests on three components: (i) agent-driven data pipelines producing large-scale, verifiable trajectories across agentic coding and agentic cowork, each grounded in an executable workspace and an artifact-aligned reward; (ii) Forge, a scalable agent-native RL system that adapts to long-horizon agent trajectories, paired with windowed-FIFO scheduling, prefix-tree merging, inference optimization, and a clean training-inference-agent decoupling that supports both white-box and black-box agents; (iii) the latest M2.7 checkpoint takes an early step toward self-evolution -- autonomously debugging training runs and modifying its own scaffold. Across M2 through M2.7, this combination translates a mini-activation footprint into frontier-tier performance on agentic coding, deep search, office-task, and reasoning benchmarks.

cs.AI↗
arXiv2026

TENT: A Declarative Slice Spraying Engine for Performant and Resilient Data Movement in Disaggregated LLM Serving

Modern GPU clusters rely on complex, heterogeneous interconnects. As large language model (LLM) serving shifts toward agentic reasoning, KVCache becomes a first-class mobile asset, driving frequent migrations and massive elephant flows that dominate the execution critical path. Operating Mooncake Transfer Engine (TE) on thousands of GPUs exposed a fundamental flaw in existing frameworks: imperative, early-binding path selection. This rigidity results in state-blind striping that ignores congestion and grey failures, leading to bandwidth stranding. This also produces operational fragility where routine faults require manual intervention. We present TENT, a declarative orchestration engine that decouples transfer intent from physical execution. By abstracting interconnects into a unified resource pool, TENT shifts path resolution from initialization to slice-time late binding. Applications simply declare transfer intents, while TENT dynamically "sprays" fine-grained slices across rails based on real-time telemetry and predictive cost modeling. This orchestration eliminates head-of-line (HoL) blocking and enables transparent, sub-50 ms self-healing by rerouting slices around failures or degradations without application-level intervention. TENT serves as the production data plane for LLM inference and reinforcement learning (RL) pipelines at multiple industrial clusters. Our evaluation shows that TE+ outperforms state-of-the-art baselines, including Mooncake TE, NIXL, and UCCL. In LLM inference with SGLang HiCache, TE+ achieves up to 1.36x higher throughput and 26% lower P90 time-to-first-token (TTFT) than Mooncake TE. In RL pipelines, TENT accelerates parameter updates in Moonshot Checkpoint Engine by 20-26%.

cs.DC↗