Strength-Parity Ensembling with Parameter-Isolated Experts for Multi-Task Affect Recognition

• URL: http://arxiv.org/abs/2607.16290v2
• Date: Tue, 21 Jul 2026 00:26:40 GMT
• Title: Strength-Parity Ensembling with Parameter-Isolated Experts for Multi-Task Affect Recognition
• Abstract summary: We build on a shared affect-latent that marginalizes the missing labels across two affect-supervised backbones.<n>An added member lowers the ensemble error only when it is both decorrelated from the current members and a near-peer of them in individual accuracy.<n>The resulting system raises the overall validation score to 1.6949, against the organizersNeXt-with-Mixment baseline of 0.45.
• Score: 4.4644619064521995
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Leading entries on the multi-task track of the 11th ABAW challenge rely on heavy ensembling, yet which member is worth adding to an already strong ensemble is rarely made explicit. We study this question for joint valence-arousal estimation, 8-way expression recognition, and 12-way action-unit detection from a single unconstrained face, under partial, long-tailed labels and a rule that forbids pretraining on Aff-Wild2. Building on a shared affect-latent that marginalizes the missing labels across two affect-supervised backbones, we propose a strength-parity rule: an added member lowers the ensemble error only when it is both decorrelated from the current members and a near-peer of them in individual accuracy. The rule exposes a concrete obstacle, as on a single backbone re-seeding and even distinct fine-tuning curricula re-converge to a prediction correlation of 0.98 and add no diversity. Parameter-isolation removes it: confining each adaptation to a disjoint low-rank subspace of a shared backbone yields experts that stay decorrelated at 0.91 while remaining near-peers, the strongest of them an AffectNet-adapted expert. The resulting system raises the overall validation score to 1.6949, against the organizers ConvNeXt-with-MixAugment baseline of 0.45; with per-AU calibration and by pooling the shared-latent heads valence-arousal byproduct as a further near-peer, the strongest configuration reaches 1.7259. Source code are available at https://github.com/cprl-team/MTL-ABAW-11th.

Related papers

• Not All Relations Are Equal: Relation-Balanced and Calibrated Graph Learning for Provenance-Based Intrusion Detection [66.44527094471619]
  We present RECAL, an unsupervised framework using relation-balanced masked graph learning to better capture rare interaction patterns.<n>On three DARPA E3 datasets, RECAL achieves F1 scores of 99.99%, 99.93%, and 99.99%, outperforming the best baseline on each dataset by 0.88, 0.82, and 0.42 percentage points, respectively.
  arXiv  Detail & Related papers  (2026-09-15T00:31:01Z)
• Beyond Magnitude: Contrastive Routing for Modular Mixture-of-Experts [7.00753296402747]
  We show that Contrastive Routing Mechanism (CoRM) scores each expert by the gap between its affinity for the incoming token and its affinity for this shared reference state.<n>Our experiments show that CoRM improves average zero-shot accuracy by +0.67 to +1.69 points (Top-1) and +1.38 to +1.77 points (Top-2) over standard Top-k MoE baselines.
  arXiv  Detail & Related papers  (2026-09-01T11:43:41Z)
• Post-Hoc Trajectory-Risk Certification for Modular LLM-Based Security Agents [1.4915002678801434]
  We show that Bonferroni allocation is distribution-free but conservative under correlated errors.<n> coarse-to-fine label selection can create near-perfect measured correlation without learned dependence.<n>A modular certificate using per-stage certificates and a pairwise overlap bound yields a positive average gain of 0.6%.
  arXiv  Detail & Related papers  (2026-08-04T23:48:36Z)
• Harnessing Disagreement: Detecting Correlated Agreement Blindness in Multi-Agent Triage [3.164789424470588]
  Disagreement-triggered escalation can create a structural blind spot in multi-agent arbitration.<n>We present ARAT, a directed-star system combining an inductive Random Forest (RF) agent, an analogical case-based k-nearest neighbour (k-NN) agent.
  arXiv  Detail & Related papers  (2026-07-22T08:35:00Z)
• The Entanglement Wall: Activation-Space Probes as Risk Detectors, Not Context Adjudicators [0.0]
  Context can change whether a request is harmful without changing its topic or surface form.<n>We ask whether residual-stream probes distinguish harmful requests from surface-matched benign controls at a useful operating point.
  arXiv  Detail & Related papers  (2026-07-12T20:37:19Z)
• PerceptionRubrics: Calibrating Multimodal Evaluation to Human Perception [75.70273182182397]
  PerceptionRubrics is a rubric-based evaluation framework.<n>It addresses the gap between saturated benchmark scores and real-world brittleness.<n>It pairs 1,038 information-dense images with over 10,000 instance-specific rubrics.
  arXiv  Detail & Related papers  (2026-06-26T17:59:15Z)
• Nous: An Attempt to Extract and Inject the Cognition Behind Prediction-Market Behavior [0.0]
  We ask whether human cognitive diversity can be recovered from behavior and transferred to LLM agents.<n>Nous extracts a structured eight-dimension behavioral profile from real Polymarket trading activity and injects it into agents through prompts.<n>We position Nous as measuring the cognitive-monoculture problem and the limits of a prompt-level remedy.
  arXiv  Detail & Related papers  (2026-06-11T08:18:25Z)
• From Observation to Intervention: A Causal Audit of Expert Importance in Mixture-of-Experts Models [0.2230291569252836]
  We investigate the use of routing statistics in Mixture-of-Experts (MoE) pruning.<n>We find no observational metric predicts causal expert importance in any model.<n>Our results provide an explicit counterexample to the common inferential step from population-level observational summaries to token-level interventional claims about expert importance.
  arXiv  Detail & Related papers  (2026-06-09T11:04:19Z)
• Let the Results Speak: A Replication-First Paradigm for LLM Behavioral Benchmarking [22.825786049667602]
  We propose a replication-first paradigm to anchor validity to a single human-rater consensus.<n>We certify the instrument via four properties -- reliability across K runs, cross-instrument replication across architecturally distinct judges, historical-footprint calibration via judges from earlier training cohorts, and pre-registered prediction.<n>We test it on emotional accompaniment by letting the self-evolve data-driven across: the dimensions are not pre-stipulated and the procedure stabilizes to a 9-dimension set.
  arXiv  Detail & Related papers  (2026-05-27T03:41:11Z)
• Neural Uncertainty Principle: A Unified View of Adversarial Fragility and LLM Hallucination [60.197429875410286]
  Adversarial vulnerability in vision and hallucination in large language models are conventionally viewed as separate problems.<n>Formalizing a Neural Uncertainty Principle (NUP) under a loss-induced state, we find that in near-bound regimes, further compression must be accompanied by increased sensitivity dispersion.<n>In vision, masking highly coupled components improves robustness without costly adversarial training.<n>In language, the same prefill-stage probe detects hallucination risk before generating any answer tokens.
  arXiv  Detail & Related papers  (2026-03-20T02:07:10Z)
• VorTEX: Various overlap ratio for Target speech EXtraction [2.9248680865344343]
  VorTEX is a text-prompted TSE architecture that separates primary extraction from auxiliary regularization pathways.<n>To enable controlled analysis, we construct PORTE, a two-speaker dataset spanning overlap ratios from 0% to 100%.<n> Experiments show that existing models exhibit suppression or residual interference under overlap, whereas VorTEX achieves the highest separation fidelity across 20-100% overlap.
  arXiv  Detail & Related papers  (2026-03-16T04:00:26Z)
• BadCLIP++: Stealthy and Persistent Backdoors in Multimodal Contrastive Learning [73.46118996284888]
  Research on backdoor attacks against multimodal contrastive learning models faces two key challenges: stealthiness and persistence.<n>We propose BadCLIP++, a unified framework that tackles both challenges.<n>For stealthiness, we introduce a semantic-fusion QR micro-trigger that embeds imperceptible patterns near task-relevant regions.<n>For persistence, we stabilize trigger embeddings via radius shrinkage and centroid alignment.
  arXiv  Detail & Related papers  (2026-02-19T08:31:16Z)
• Explicit Tradeoffs between Adversarial and Natural Distributional Robustness [48.44639585732391]
  In practice, models need to enjoy both types of robustness to ensure reliability. In this work, we show that in fact, explicit tradeoffs exist between adversarial and natural distributional robustness.
  arXiv  Detail & Related papers  (2022-09-15T19:58:01Z)
• Relabel the Noise: Joint Extraction of Entities and Relations via Cooperative Multiagents [52.55119217982361]
  We propose a joint extraction approach to handle noisy instances with a group of cooperative multiagents. To handle noisy instances in a fine-grained manner, each agent in the cooperative group evaluates the instance by calculating a continuous confidence score from its own perspective. A confidence consensus module is designed to gather the wisdom of all agents and re-distribute the noisy training set with confidence-scored labels.
  arXiv  Detail & Related papers  (2020-04-21T12:03:04Z)

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.