ValueFormer: A Causal Transformer Value Function with Stage-Aware Labels for Semi-Autonomous Vision-Language-Action Policies

• URL: http://arxiv.org/abs/2608.02958v1
• Date: Mon, 03 Aug 2026 23:46:39 GMT
• Title: ValueFormer: A Causal Transformer Value Function with Stage-Aware Labels for Semi-Autonomous Vision-Language-Action Policies
• Abstract summary: We present ValueFormer, a compact policy-a causal transformer over a frozen DINOv3 backbone.<n> Failed episodes are labeled with a stage-aware, success-then-decay return that preserves the success curve before the failure stage, and detection is supervised from mistake intervals rather than a single failure time.
• Score: 0.576537956677604
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Vision-Language-Action (VLA) policies trained by behavior cloning fail silently: from the action stream alone, a collapsing rollout looks much like one making clean progress, because imitation supplies no notion of progress. Reinforcement learning would supply one, but it is impractical here, where real-robot experience is costly and deformable food resists simulation. The cheap alternative, a terminal success / failure bit, is learnable in principle yet far too sparse to say when a rollout went wrong. We argue that the per-frame label, not the architecture, is the hard part: to be useful it must be dense, continuous, and correctly shaped. We present ValueFormer, a compact policy-agnostic causal transformer over a frozen DINOv3 backbone that emits two per-frame signals in one forward pass: a smooth Monte Carlo value, V_mc, for advantage estimation and a sharp binary value for online mistake detection, targets that pull in opposite directions by design. Failed episodes are labeled with a stage-aware, success-then-decay return that preserves the success curve before the failure stage, and detection is supervised from mistake intervals rather than a single failure time, so mistakes the policy recovers from also carry signal. On a real-robot bimanual sandwich-assembly task 1,427 episodes), a critic-derived per-frame training weight lifts task completion from 70% to 85% (within noise at n=20), and a batched bf16 encoder cuts the live serving cost 3~5 times so the critic runs at 2 Hz alongside the policy on a single GPU.

Related papers

• Where Success Breaks: Failure-Boundary Learning for Robust Vision-Language-Action Models [47.715495058757824]
  Vision--action (VLA) models adapted through supervised fine-tuning (SFT) inherit a structural asymmetry.<n>We argue that robust VLA adaptation should be viewed not as further demonstration fitting, but as **Failure-Boundary Learning'
  arXiv  Detail & Related papers  (2026-09-05T14:24:16Z)
• DemoBridge: A Simulation-in-the-Loop Toolkit for Single-View Human Demonstration Retargeting [49.70827726228219]
  We present DemoBridge, a toolkit that turns a single-view RGB stereo recording of a human hand demonstration into an executable, physics-validated robot-arm trajectory.<n>At the core of DemoBridge is a single collision-aware planner.<n>A physics simulator runs in the loop. It validates each phase as it is produced and backtracks on failure, so a demonstration that cannot be reproduced as given is re-planned rather than discarded.
  arXiv  Detail & Related papers  (2026-07-10T15:31:04Z)
• Sequential Planning via Anchored Robotic Keypoints [3.176338968032152]
  We present Sequential Planning via Anchored Robotic Keypoints, SPARK, a training-free neurosymbolic manipulation system.<n>A single Gemini call composes the plan as a typed behavior tree (BT) of composable kinematic primitives.<n>A second Gemini call proposes three alternative text prompts per object, SAM3 evaluates each, and we keep the prompt$to$label pair with the most confident detection.<n>The alternative prompts add +27.7 points on the spatial suite and +10.0 on the object suite, with the recovery loop adding +5.0 overall.
  arXiv  Detail & Related papers  (2026-06-29T17:48:01Z)
• Perfect Demo Makes Poor Teacher: Learning Robust Alignment from Critical Motion Segments [53.85970147743299]
  Expert demonstrations are widely assumed to be the gold standard for robot imitation learning.<n>Yet for fine-grained manipulation such as insertion, stacking, and alignment, we uncover a counterintuitive failure mode: fluent demonstrations can be poor teachers.<n>We introduce STAIR, a compact dynamic feature that bridges the vision-language model and the action expert, distilling the short-horizon motion already recorded in each trajectory into dense, motion-aware supervision.
  arXiv  Detail & Related papers  (2026-06-14T04:15:29Z)
• Capability and Robustness Cannot Both Be Free: An Information-Theoretic Bound for Vision-Language-Action Models [0.0]
  Vision-Language-Action (VLA) models reach high success rates on clean inputs but collapse under small adversarial perturbations.<n>We prove that a $16/255$ PGD attack drops OpenVLA-7B's LIBERO success from $95%$ to under $5%$.<n>For any VLA policy, capability $I(Astar;Api)$ and robustness $I(Api;Atildepi)-I(Api;)$ sum to at most $H(Astar)+I(X;Xt
  arXiv  Detail & Related papers  (2026-05-25T14:16:57Z)
• Survive or Collapse: The Asymmetric Roles of Data Gating and Reward Grounding in Self-Play RL [76.45061154544568]
  Self-play reinforcement learning trains language models on their own generated tasks, co-evolving a proposer and solver without human labels.<n>Recent systems report strong reasoning gains, but collapse and instability are widely observed and poorly understood.<n>We argue instead that self-play stability is governed by two distinct levers: a data-level gate that decides which proposer-generated tasks enter the training pool, and the reward signal that updates the policy on tasks already admitted.
  arXiv  Detail & Related papers  (2026-05-21T09:19:23Z)
• ReCoVer: Resilient LLM Pre-Training System via Fault-Tolerant Collective and Versatile Workload [18.933354857797056]
  Pre-training large language models on massive GPU clusters has made hardware faults routine rather than rare.<n>We propose ReCoVer, a resilient pre-training system that upholds a single invariant.<n>For comparison with checkpoint-and-restart baselines, ReCoVer demonstrates $2.23times$ higher effective throughput after successive failures.
  arXiv  Detail & Related papers  (2026-05-11T20:28:31Z)
• Guardian: Detecting Robotic Planning and Execution Errors with Vision-Language Models [53.20969621498248]
  We propose an automatic robot failure synthesis approach that procedurally perturbs successful trajectories to generate diverse planning and execution failures.<n>We construct three new failure detection benchmarks: RLBench-Fail, BridgeDataV2-Fail, and UR5-Fail.<n>We then train Guardian, a VLM with multi-view images for detailed failure reasoning and detection.
  arXiv  Detail & Related papers  (2025-12-01T17:57:27Z)
• Reinforcement Learning with Verifiable yet Noisy Rewards under Imperfect Verifiers [90.50039419576807]
  Reinforcement Learning with Verifiable Rewards (RLVR) trains policies against automated verifiers to avoid costly human labeling.<n>To reduce vulnerability to verifier hacking, many RLVR systems collapse rewards to binary $0,1$ during training.<n>This choice carries a cost: it introduces textitfalse negatives (rejecting correct answers, FNs) and textitfalse positives (accepting incorrect ones, FPs)
  arXiv  Detail & Related papers  (2025-10-01T13:56:44Z)
• Abduct, Act, Predict: Scaffolding Causal Inference for Automated Failure Attribution in Multi-Agent Systems [20.846301581161978]
  Failure attribution in multi-agent systems is a critical yet unsolved challenge.<n>Current methods treat this as a pattern recognition task over long conversation logs.<n>A2P Scaffolding transforms failure attribution from pattern recognition into a structured causal inference task.
  arXiv  Detail & Related papers  (2025-09-12T16:51:15Z)
• WR-ONE2SET: Towards Well-Calibrated Keyphrase Generation [57.11538133231843]
  Keyphrase generation aims to automatically generate short phrases summarizing an input document. The recently emerged ONE2SET paradigm generates keyphrases as a set and has achieved competitive performance. We propose WR-ONE2SET which extends ONE2SET with an adaptive instance-level cost Weighting strategy and a target Re-assignment mechanism.
  arXiv  Detail & Related papers  (2022-11-13T09:56:24Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.