SemRF: A Semantic Reference Frame for Residual-Stream Dynamics in Language Models

• URL: http://arxiv.org/abs/2606.32022v1
• Date: Tue, 30 Jun 2026 17:52:22 GMT
• Title: SemRF: A Semantic Reference Frame for Residual-Stream Dynamics in Language Models
• Abstract summary: SemRF is an anchor-based formalism separating semantic measurement from residual dynamics.<n>A SemRF fixes anchors and measures states against them.<n>With the frame fixed, residual computation becomes a depthwise semantic trajectory.
• Score: 22.84428628659889
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Residual-stream analysis asks how language-model computation evolves across depth, but intermediate decoding requires comparable readout coordinates across layers. If embedding anchors and unembedding readout disagree on the chosen span, apparent motion may reflect measurement drift rather than computation. We introduce \emph{Semantic Reference Frames} (SemRF), an anchor-based formalism separating semantic measurement from residual dynamics. A SemRF fixes anchors and measures states against them. Pseudo-inverse tying gives exact synchronization; under restricted bi-invertibility, SemRF yields stable semantic-basis coordinates, distortion bounds, and near-identity changes. With the frame fixed, residual computation becomes a depthwise semantic trajectory. The anchors induce a semantic Voronoi diagram: distance, or evidence such as logits, assigns each layer to a coarse cell, while coordinates retain within-cell motion and margins. We define layerwise steps, contribution profiles, and imbalance diagnostics, then use the Voronoi trace to define a margin-relaxed tube. The canonical trace is the minimum-action path inside this tube; when nonempty with positive quadratic weight, it is unique and obeys a discrete spline equation away from active constraints. Excess action controls step, curvature, and profile mismatch. Low curvature implies piecewise-linear compressibility and local knowledge density: lower trace complexity means fewer semantic knots. Through the parameter-to-trajectory map, this gives a conditional link to parameter efficiency: among admissible settings fitting data, lower-action and lower-complexity traces use fewer semantic degrees of freedom. The guarantees require controlled interface error and small projection residual under explicit tube constraints.

Related papers

• Balancing Emotional Alignment and Semantic Consistency in Image Generation via Reinforcement Learning with Valence-Arousal Anchoring [55.57242007016976]
  Continuous emotion control in text-to-image generation requires a model to improve affective alignment without changing the objects, layout, or scene described by the prompt.<n>Existing supervised emotion-injection methods often optimize feature-space proxies and may therefore exhibit emotion-semantic drift.<n>We address this problem with a flow-matching image-generation framework that combines continuous valence-arousal conditioning, Group Relative Policy Optimization, and a neutral semantic anchor.
  arXiv  Detail & Related papers  (2026-09-11T13:24:35Z)
• Feasibility and Memory Mechanisms of Chern-Simons Context Reservoir Computation [0.0]
  We investigate whether a Chern-Simons context reservoir is a viable computational substrate.<n>To separate generic reservoir behavior from gauge-specific effects, we compare four matched models.<n>We find a task-specific advantage for geometry- and order-sensitive processing, rather than generic reservoir superiority.
  arXiv  Detail & Related papers  (2026-09-10T17:45:30Z)
• Statistical Symmetry Release for Equivariant Quantum Learning [12.042012916861829]
  Hard symmetry constraints reduce model complexity, but can also erase label information.<n> Statistical symmetry release determines when finite data and quantum measurements justify relaxing such a constraint.
  arXiv  Detail & Related papers  (2026-09-10T12:38:27Z)
• Drift and Dependence: Layer-wise Information-Theoretic Bounds for Replay-Based Continual Learning [41.371439825328544]
  Continual learning must absorb new tasks without erasing old ones, and replay---mixing a small buffer of past examples into current training---is among the most effective remedies for catastrophic forgetting.<n>We develop a layer-wise information-theoretic framework that separates these effects at every depth.<n>Controlled and benchmark experiments confirm the predicted memory scaling, the interior funnel, and the alignment signal's link to forgetting.
  arXiv  Detail & Related papers  (2026-08-12T06:01:49Z)
• Geodesic Flow Matching for Denoising High-Dimensional Structured Representations [1.267635674675289]
  For continuous domains, Spatial Semantic Pointers (SSPs) extend this framework by mapping variables onto continuous toroidal manifold.<n>Standard approaches like Flow Matching assume a flat Euclidean geometry, which fails to account for the geometric constraints imposed on valid SSP states.<n>We demonstrate that this assumption fails for SSPs: Euclidean linear interpolants cut through" the manifold's interior, destroying the phase and magnitude structure required for accurate decoding.
  arXiv  Detail & Related papers  (2026-05-29T18:28:41Z)
• Metric--Phase Fields: Decoupling Distance and Sign for Thin-Structure Reconstruction from Unoriented Point Clouds [67.30236447078187]
  We introduce Metric-Phase Fields (MPFs), a decoupled implicit representation that separates metric proximity from topological phase.<n>Experiments on both synthetic and scanned thin-shell and thin-plate shapes demonstrate that MPFs preserve thin and layered structures more faithfully than recent SDF-based methods.
  arXiv  Detail & Related papers  (2026-05-25T07:08:57Z)
• Reading Calibrated Uncertainty from Language Model Trajectories [46.663987199083245]
  Methods that probe the model's internal activations feed raw hidden states into opaque snapshots and leave implicit the layer-wise trajectory by which a representation is formed.<n>We extract eleven scale-invariant geometric features, tracing the cumulative path of per-layer updates, and feed them to a sparse linear probe.<n>The probe outperforms MSP under selective abstention, with baseline scaling with up to 21 AURC points.
  arXiv  Detail & Related papers  (2026-05-19T19:24:29Z)
• Provable Sparse Inversion and Token Relabel Enhanced One-shot Federated Learning with ViTs [77.42033827176806]
  One-Shot Federated Learning, where a central server learns a global model in a single communication round, has emerged as a promising paradigm.<n>We propose a novel Federated Model Inversion and Token Relabel framework, which trains the global model by fully exploiting all patches of synthetic images.
  arXiv  Detail & Related papers  (2026-05-11T15:49:08Z)
• Recovering Physical Dynamics from Discrete Observations via Intrinsic Differential Consistency [12.266189649117003]
  We replace local supervision with a global structural constraint.<n>We train a time-conditioned secant velocity field whose deviation from this property serves two purposes.<n>As a training regularizer, it confines the hypothesis space to flows that compose consistently across temporal scales.
  arXiv  Detail & Related papers  (2026-05-08T20:24:32Z)
• Unbiased Gradient Estimation for Event Binning via Functional Backpropagation [64.88399635309918]
  We propose a novel framework for unbiased gradient estimation of arbitrary binning functions by synthesizing weak derivatives during backpropagation.<n>We achieve 9.4% lower EPE in self-supervised optical flow, and 5.1% lower RMS error in SLAM, demonstrating broad benefits for event-based visual perception.
  arXiv  Detail & Related papers  (2026-02-13T04:05:03Z)
• Asymptotic Semantic Collapse in Hierarchical Optimization [0.5729426778193398]
  Multi-agent language systems can exhibit a failure mode where a shared dominant context progressively absorbs individual semantics.<n>We study this effect under the name Asymptotic Semantic Collapse in Hierarchical Optimization.<n>We show that repeated interactions with Peripheral Agent Nodes drive an alignment that minimizes a global loss.
  arXiv  Detail & Related papers  (2026-02-01T00:02:01Z)
• Riemannian Flow Matching for Disentangled Graph Domain Adaptation [51.98961391065951]
  Graph Domain Adaptation (GDA) typically uses adversarial learning to align graph embeddings in Euclidean space.<n>DisRFM is a geometry-aware GDA framework that unifies embedding and flow-based transport.
  arXiv  Detail & Related papers  (2026-01-31T11:05:35Z)
• Verifying Closed-Loop Contractivity of Learning-Based Controllers via Partitioning [52.23804865017831]
  We address the problem of verifying closed-loop contraction in nonlinear control systems whose controller and contraction metric are both parameterized by neural networks.<n>We derive a tractable and scalable sufficient condition for closed-loop contractivity that reduces to checking that the dominant eigenvalue of a symmetric Metzler matrix is nonpositive.
  arXiv  Detail & Related papers  (2025-12-01T23:06:56Z)
• Learning by Neighbor-Aware Semantics, Deciding by Open-form Flows: Towards Robust Zero-Shot Skeleton Action Recognition [41.77490816513839]
  We propose a novel method for zero-shot skeleton action recognition, termed $texttt$textbfFlora$$.<n>Specifically, we attune textual semantics by incorporating direction-aware regional semantics, and a cross-modal consistency objective.<n>Experiments on three benchmark datasets validate the effectiveness of our method, showing particularly impressive performance even when trained with only 10% of the seen data.
  arXiv  Detail & Related papers  (2025-11-12T14:54:53Z)
• SimT: Handling Open-set Noise for Domain Adaptive Semantic Segmentation [58.61946589036262]
  This paper studies a practical domain adaptive (DA) semantic segmentation problem where only pseudo-labeled target data is accessible through a black-box model. Due to the domain gap and label shift between two domains, pseudo-labeled target data contains mixed closed-set and open-set label noises. We propose a simplex noise transition matrix (SimT) to model the mixed noise distributions in DA semantic segmentation and formulate the problem as estimation of SimT.
  arXiv  Detail & Related papers  (2022-03-29T02:48:08Z)

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.