Searcharxiv⌕ Search

arXiv subjects

Yuhan Liu

Publications and source records attributed to Yuhan Liu.

At least 19 recordsLinked to original sources
arXiv2026

PolicyIK: High-Precision Inverse Kinematics for Robot Arms with Reinforcement Learning

Inverse kinematics (IK) converts end-effector pose commands into joint motion, and many vision-language-action (VLA) policies rely on it to act on a given arm and to transfer across embodiments. Precise IK remains laborious: redundancy and singularities complicate the inverse mapping, execution depends on hand-tuned controllers, and training data on physical robots are costly to collect. We present PolicyIK, a goal-conditioned reinforcement learning policy for high-precision IK. It updates joint-position references from pose feedback and observes its accumulated reference relative to the measured joints, so it can retain the offset that the position controller needs at rest. Two-scale pose errors with an error-dependent action gain resolve millimeter residuals while preserving large motions. Progress and dwell rewards teach it to both reach the tolerance and stay within it. In simulation, a single attempt by the trained PPO policy keeps the mean errors over the final second within 1 mm and 0.2° on 93.5% of held-out tasks, and a deployment protocol raises success to 98.9%. When trained directly on a physical arm with an off-policy RL learner, PolicyIK achieves higher reaching and holding success than all four classical IK controllers under the same time budgets. In simulated pick-and-place, PolicyIK executes the end-effector commands of the $π_{0.5}$ VLA policy with 95.7% success. These results show that reinforcement learning can provide high-precision inverse kinematics for robot arms. Code is available at https://github.com/Tinaliu0123/PolicyIK.

cs.RO↗
arXiv2026

PolyDiscover: an integrated trust-aware platform for multi-objective polymer discovery and simulation validation

Data-driven polymer discovery remains fragmented across databases, models, screening, literature, and simulations. We present PolyDiscover, a platform unifying multi-source property lookup, graph-neural-network prediction, trust-aware multi-objective screening, literature extraction, generative candidate exploration, and automated handoff to molecular-dynamics validation. Building on published ADEPT-PolyGraphMT, it harmonizes experimental, molecular-dynamics, density-functional-theory, and group-contribution data spanning 28 properties across about 13,000 real and one million virtual polymers. Its engine combines feasibility filtering and exact Pareto ranking with a trust score integrating similarity to known polymers, physical consistency, predictive uncertainty, and synthesizability, followed by diversity-aware shortlisting. Two case studies on lightweight, thermally stable structural materials and thermally stable electrical insulators, using monomer HOMO-LUMO gap as an insulation proxy, reduced a million-polymer search space to 30 chemically diverse candidates per task. Higher-fidelity molecular-dynamics and density-functional-theory calculations, interpreted after correcting systematic density underestimation by the molecular-dynamics protocol, showed retention of targeted property combinations. Ablation showed that trust-aware ranking shifted about one fifth of each shortlist toward more synthesizable chemistry closer to known polymers. A constrained natural-language interface translated a free-text request into a validated specification matching expert screening exactly, while staged literature evidence corroborated high glass-transition temperatures in polyimide-dominated shortlists against published experiments. PolyDiscover offers a traceable route from design intent to simulation-validated candidates, easing exploration of polymer chemical space.

physics.chem-ph↗
arXiv2026

FVH-Bench: Evaluating Image Generator Safety Beyond Overtly Harmful Imagery

Modern image generators can produce complex visual artifacts, including diagrams, interfaces, and records that combine text, graphics, and layout to convey detailed information. They may refuse requests for overtly harmful imagery yet still generate artifacts that guide dangerous actions or support deception. We call the risk arising from what such images enable, rather than only what they depict, functional visual harm (FVH). Existing safety benchmarks focus largely on overtly harmful content, such as pornography and graphic violence, leaving image generators' safety alignment against FVH insufficiently evaluated. To address this gap, we introduce FVH-Bench, comprising 669 prompts across five harmful visual functions and ten risk domains. The 11 evaluated image generators rarely refuse these requests and frequently generate artifacts that fulfill the targeted harmful functions. High scores for target harm realization and harmful artifact usability further indicate that these outputs can support the intended harmful purposes. A further analysis finds that existing safety detectors also provide limited coverage of FVH, indicating gaps in their ability to recognize harmful visual functions. Together, these findings show that evaluating image-generator safety alignment requires considering not only what images depict, but also what they may enable.

cs.CR↗
arXiv2026

SceneBloom: Agentic Indoor Environment Generation with Realistic and Diverse Layouts for Embodied Learning

Training generalizable embodied agents requires realistic, varied, and simulation-ready indoor environments. Language-guided methods support semantic planning and object-level reasoning, but precise spatial grounding remains difficult. Visual generative models offer rich priors over plausible arrangements, yet their outputs require geometric reasoning to become physically valid 3D scenes. We introduce SceneBloom, an agentic framework that combines visual layout sampling with contract-guided 3D compilation. A hierarchical sampler uses diffusion priors to generate furniture arrangements within functional zones. A compiler then uses relations extracted from each proposal to guide geometric fitting and local pose correction. Across five room types, SceneBloom attains the highest visual quality and physical stability among the compared methods and is the only method with no detected mesh collisions and out-of-bounds objects. Its layouts are also closer to the distribution of real rooms than those of all compared baselines. Object navigation policies trained in these realistic scenes achieve a higher success rate in held-out real scans than those trained on an equal number of real training scans. Code is available at https://github.com/Tinaliu0123/scenebloom.

cs.CV↗
arXiv2026

TTCS: Test-Time Curriculum Synthesis for Self-Evolving

Test-Time Training offers a promising way to improve the reasoning ability of large language models (LLMs) by adapting the model using only the test questions. However, existing methods struggle with difficult reasoning problems for two reasons: raw test questions are often too difficult to yield high-quality pseudo-labels, and the limited size of test sets makes continuous online updates prone to instability. To address these limitations, we propose TTCS, a co-evolving test-time training framework. Specifically, TTCS initializes two policies from the same pretrained model: a question synthesizer and a reasoning solver. These policies evolve through iterative optimization: the synthesizer generates progressively challenging question variants conditioned on the test questions, creating a structured curriculum tailored to the solver's current capability, while the solver updates itself using self-consistency rewards computed from multiple sampled responses on both original test and synthetic questions. Crucially, the solver's feedback guides the synthesizer to generate questions aligned with the model's current capability, and the generated question variants in turn stabilize the solver's test-time training. Experiments show that TTCS consistently strengthens the reasoning ability on challenging mathematical benchmarks and transfers to general-domain tasks across different LLM backbones, highlighting a scalable path towards dynamically constructing test-time curricula for self-evolving. Our code and implementation details are available at https://github.com/XMUDeepLIT/TTCS.

cs.LG↗
arXiv2026

What a One-Hour Interview Does Not Tell an LLM About You: Interviews Elicit Traits, Not Decision Policies

Large language models are increasingly asked to stand in for particular people, and interviewing the person is the natural way to tell a model who they are. We test what a one-hour LLM-led adaptive interview tells a model about an individual's value-laden decisions. 46 adults completed such an interview and then answered 25 dilemma questions, which are the ground truth. We predict their answers from different parts of the transcript, compare adaptive follow-up questions with fixed ones on the same participants, and benchmark every variant against a model given no information about the person and against the majority answer. No part of the interview is reliably better than either baseline, and adaptive follow-ups are no better than fixed ones. Two audits of the transcripts show why. For 85% of the errors an auditor finds no evidence that distinguishes the person's choice from the alternatives, and where a transcript does contain related evidence, the option it favours matches the person's own answer less often than the majority answer does. The same transcripts do improve recovery of the person's MBTI type. Interviews of this kind elicit traits, not decision policies. We discuss what decision-aware elicitation would require and why persona agents should not be delegated value-laden decisions, and we release the consenting participants' transcripts with all predictions.

cs.CL↗
arXiv2026

LAMB: Latent Multi-Hypothesis Beliefs for Long-Horizon Large Language Agents

Long-horizon language agents require compact memories that retain interaction evidence while preserving competing hypotheses about unobserved states. Although effective, many belief-state methods encode memory in discrete natural language, where repeated compression can omit evidence or prematurely discard plausible alternatives. We introduce LAMB, a recurrent framework for latent multi-hypothesis beliefs. A Common--Delta factorization combines a shared Common state for interaction evidence with weighted Delta components for competing hypotheses. Relative evidence from action-outcome predictions guides recurrent hypothesis updates without generating textual memory. A context-conditioned readout exposes hypotheses separately to the policy through a fixed-token belief prefix in the default configuration. The belief modules and policy are jointly trained using action imitation and auxiliary state, outcome, and observation-discrimination objectives. Across ALFWorld, BabyAI, ScienceWorld, and Crafter, LAMB matches or outperforms PABU, improving ALFWorld SR@30 and ScienceWorld success by 6.0 and 22.0 percentage points, respectively, and Crafter achievement progress by 26.37 points. On ALFWorld, it also reduces the redundant-action rate by 17.70 percentage points. These results support latent multi-hypothesis beliefs as compact memory for effective long-horizon decision making

cs.CL↗
arXiv2026

Evo-B&B: Behavior-Aware LLM-Guided Joint Evolution of Branching and Node Selection Policies for MILP

In branch-and-bound for Mixed-Integer Linear Programming (MILP), branching and node selection are two critical and tightly coupled decisions, yet most existing learning-based approaches focus on optimizing them separately. We propose Evo-B&B, an LLM-guided evolutionary framework that jointly evolves executable branching and node selection policies using end-to-end SCIP solving feedback. To improve search efficiency and reduce redundant evaluations of behaviorally similar policies, Evo-B&B introduces a behavior-aware multi-island evolutionary mechanism. It measures policy similarity from branching and node-selection behaviors on a fixed set of B&B decision states and uses this similarity to preserve population diversity. We evaluate Evo-B&B on four standard MILP benchmarks across multiple instance scales. Experimental results show that Evo-B&B achieves competitive solving performance and generalizes well to larger-scale instances, while ablation studies further demonstrate the effectiveness of joint evolution and behavior-aware diversity management.

cs.AI↗
arXiv2026

Multi-Teacher On-Policy Distillation for Flow-Based Vision-Language-Action Models

Specialized vision-language-action (VLA) policies acquire strong domain-specific skills, yet consolidating these skills into one shared policy remains challenging. On-policy distillation (OPD) transfers teacher knowledge on inputs induced by the student, addressing the distribution mismatch encountered during deployment. For flow-based VLAs, this mismatch arises at two levels: environment observations and intermediate action-generation states. We propose a two-level on-policy distillation framework that couples student-driven environment interaction with teacher velocity supervision along student-generated action flow trajectories. Frozen domain specialists jointly supervise one student. After each update, the student collects new environment experience and generates fresh action-flow trajectories. Starting from a joint supervised fine-tuning (SFT) initialization, Velocity Loss OPD yields absolute success-rate gains of 22.55% on LIBERO-40, 33.4% on CALVIN five-instruction sequences, and 22.6% on Meta-World MT50. Compared with Action Loss OPD and Teacher-rollout SFT, it achieves absolute success-rate gains of 6.4-9.5% on LIBERO-40, 9.7-18.3% on CALVIN, and 3.2-4.2% on Meta-World MT50. Analysis by sequence length further shows larger success-rate gains on longer CALVIN sequences. These results demonstrate effective multi-domain capability consolidation through two-level on-policy supervision, with a single student deployed across domains.

cs.RO↗
arXiv2026

Frame-Wise Streaming for Efficient Learned Speech Compression

Speech compression is increasingly important in scenarios such as real-time and satellite communication. Neural codecs have shown superior Rate-Distortion (RD) performance over traditional signal-processing codecs. Models with long-range dependency encoders/decoders and entropy models outperform convolution-based structures, but they still lack streaming support since they rely on sequence-level correlations. In this paper, we propose StreamLSC, a frame-level streaming learned speech compression model built on three fundamental components of streaming networks, i.e. Boundary-Cached Causal Convolution, Intra-Frame Layer Normalization, and RNN-mode RWKV. Our model incorporates a streamable entropy quantizer module, ensuring efficient context model while preserving causal constraints. Experiments show that the streaming model achieves performance comparable to its offline counterpart, attaining state-of-the-art rate-distortion results, significant gains in subjective evaluations, -51.37% (ViSQOL) and -53.99% (PESQ) BD-RATE savings on average, and improvements of 0.2154 and 0.5156 in BD-ViSQOL and BD-PESQ.

cs.SD↗
arXiv2026

CoMMa: Contribution-Aware Medical Multi-Agents for Decentralized Oncology Decision Support

Recent multi-agent frameworks have shown promise for oncology decision support, yet most assume centralized data access and rely on prompt-based assignment, limiting their applicability in privacy-sensitive clinical settings. We propose Contribution-Aware Medical Multi-Agents (CoMMa), a decentralized LLM-agent framework where specialists operate on partitioned clinical data streams. Unlike prior approaches that share inputs across agents, CoMMa enforces data decentralization to include stronger role specialization and further enhances this via agent-specific finetuning. To enable reliable and interpretable coordination, we introduce a contribution-aware aggregation mechanism that replaces stochastic, narrative-based reasoning with deterministic embedding projections to approximate each agent's marginal utility. This yields explicit credit assignment over agents, providing a stable and interpretable decision pathway aligned with clinical requirements. We evaluate CoMMa on multiple oncology benchmarks, including real-world multidisciplinary tumor board datasets from large academic hospitals in North America and East Asia, as well as public datasets, demonstrating strong performance and generalization across heterogeneous clinical settings.

cs.AI↗
arXiv2026

Which Skill to Distill? SGUID: Selecting a Compact Skill Bank for Model-Skill Co-Evolution

Skills, reusable procedural guidance added at inference, can substantially improve LLM downstream performance (Li et al., 2026). Prior work retrieves skills from a bank by semantic relevance, then uses them as inference-time patches or for model distillation. The individual utility of each skill, however, is largely neglected. We first show that, in on-policy distillation where skill-conditioned policies serve as teachers, fewer than 25% of retrieved skills provide useful distillation signals. We then propose SGUID, a method for selecting a compact subset of skills for distillation. SGUID retains a skill only if it consistently yields effective learning signals during training. The selected skills are then distilled to produce a better model. Our results show that not all skills are worth distilling. Across four models from the Olmo and Qwen families, distilling 6 selected skills matches or exceeds full-bank distillation in mean avg@12 on three of the four models, and on all four after a second round that distills 3 newly selected skills, while the full banks are up to 11x larger. Importantly, SGUID supports stable model-skill co-evolution: after a distillation round, a new candidate bank is curated from the updated model's rollouts, and SGUID selects which skills to internalize next. In the second round, this loop selects 3 new skills and improves Qwen3-8B from 64.3% to 66.3%. The selection step is essential for stability: on Qwen3-4B, naively updating the model with unfiltered skills degrades performance, including a 0.3 percentage point drop on HMMT25, whereas SGUID improves HMMT25 by 0.5 points after the first round and 1.1 points after the second. These results identify skill selection as the key mechanism for stable model-skill co-evolution.

cs.CL↗
arXiv2026

How Much Evidence Should a Coding Agent's Self-Correction Carry? Adaptive Dirichlet Evidence for Self-Distillation

Execution feedback lets coding agents revise programs and learn from their own corrections. A correction's learning weight should reflect both the transitions supported by its executions and the amount of evidence behind that support. We introduce Effective-Evidence Self-Distillation (EESD), which represents these quantities separately. Normalized execution relevance determines relative transition support and an effective pseudo-count mass; a Dirichlet posterior then produces an uncertainty-penalized weight for KL-anchored correction learning. Under a symmetric prior, changing mass preserves category ordering, and effective mass yields a supervised coefficient bounded by its matched fixed-mass counterpart. Across four model-domain history sweeps, increasing visible observations from one to eight reduces future-outcome NLL by 55.0-59.3%. At eight observations, effective mass achieves lower NLL than fixed mass in all four comparisons. In the primary matched DeepSeek/RunBugRun study, argmax predictions agree on all 3,000 examples, with the largest NLL gain under concentrated relevance. After one correction-learning round, DeepSeek/CodeARC all-tests Pass@1 increases from 15.0% to 20.4%, with a paired 95% source-bootstrap interval of [+2.8, +8.0] percentage points. The twelve-setting downstream evaluation establishes the model-domain scope of this update. These results show how separating evidence support from evidence mass changes probability estimation and correction learning in coding agents.

cs.AI↗
arXiv2026

ParaGeo: Decomposing Paralinguistic Variation into a Shared Latent Geometry

Speech delivery varies with both the requested paralinguistic attribute and the linguistic content. We introduce ParaGeo, a matched-content decomposition of paralinguistic variation in a frozen speech language model. Synthesized audio tokens are replayed with a fixed listening prompt; pooled key/value (K/V) representations are centered and projected into a shared low-dimensional space. Our GLM-4-Voice probe spans 80 requested controls from 12 benchmark families across eight sentences. With a globally fitted calibration basis, content-held-out centroid accuracy using this basis is 9.49% versus a 1.25% permutation baseline; same-label cross-content cosine similarity is 0.285 versus 0.017, and both conditional permutation tests yield p = 0.001. A separate ten-scenario, six-style probe reveals reproducible contrast directions across scenarios. Static, additive, and temporal interventions produce attribute-, layer-, and schedule-dependent response profiles. These results provide a shared coordinate representation for measuring paralinguistic structure and an empirical starting point for latent speech control. Code is available at https://github.com/yuhanlydia/ParaGeo.

cs.SD↗
arXiv2026

Beyond Policy Alignment: Closing the Planning-Learning Loop for Robot Control with Learned World Models

Planning with learned world models combines online trajectory optimization with learned value and policy functions for high-dimensional control. Because the planner determines the experience used for learning, while the learned critic and actor in turn score and propose future plans, planning and learning form a closed feedback loop. TD-MPC is a prominent instance of this design. Recent policy-constrained variants strengthen one part of the loop by aligning the learned policy with planner behavior. We introduce PL-MPC (Planning-Learning MPC), which additionally modifies critic supervision and planner terminal-value estimation. Hybrid multi-step TD targets expose critic updates to more realized rewards before bootstrapping; disagreement-aware terminal estimates reduce the influence of uncertain critic values during MPPI planning; and return-weighted actor distillation emphasizes planner-executed actions from high-return episodes. The world-model architecture and MPPI optimizer are otherwise unchanged. On HumanoidBench, the largest gains occur on \texttt{balance-hard}, where Total Average Return (TAR) increases from $98\pm18$ to $387\pm255$, and \texttt{hurdle}, from $199\pm13$ to $466\pm200$; performance across the broader benchmark remains task dependent, and PL-MPC remains competitive on DMControl. Controlled ablations show different component interactions across the two tasks. We further demonstrate zero-shot sim-to-real transfer on wrench-nut alignment with a 7-DoF KUKA IIWA14, obtaining higher observed success than TD-M(PC)^2 on the training object size and two unseen sizes. Code and data will be available at: https://pl-mpc-humanoid.github.io.

cs.RO↗
arXiv2026

The power of oracle access: Optimal sample and query complexity of the abelian state hidden subgroup problem

In the quest to identify further quantum algorithms exhibiting superpolynomial speed-ups, a recurring theme is that the complexity of a problem is largely shaped by the input access model. Here, we study this phenomenon for the state hidden subgroup problem (StateHSP), a quantum generalization of the hidden subgroup problem in which the goal is to identify the symmetries of an unknown quantum state. For finite abelian groups, existing Fourier-sampling algorithms use $O(\log(|G|)/ε)$ copies of the state, but whether this scaling is optimal has remained open. We settle the complexity of the abelian StateHSP in both the previously studied sample model and a new query model, which is a stronger and operationally natural generalization that provides access to the state-preparation unitary and its inverse. In the query model, we give a time-efficient quantum algorithm using $O(\log(|G/H|)/\sqrtε)$ forward and inverse queries, and prove a matching $Ω(\log(|G/H|)/\sqrtε)$ lower bound which holds even in the stronger conjugate-query and controlled-query settings. By contrast, we show that in the sample model, $Θ(\log(|G/H|)/ε)$ copies are both sufficient and information-theoretically necessary, even if one allows for arbitrary collective measurements. Thus, the quadratic improvement in $ε$ genuinely arises from coherent access to the preparation circuit. As applications, we obtain faster algorithms for learning stabilizer groups, locating unentanglement, and identifying hidden translation symmetries.

quant-ph↗