Goal-conditioned reinforcement learning hinges on how the goal is encoded. Contrastive, metric, temporal-distance, and information-theoretic encoders differ in objective. They still share one trait. None of them sees the current state. Such a state-independent embedding cannot mark which part of the goal still needs action. The policy must then recover that cue by inverting both encoders. We propose DAGR. It refines the static embedding of any late-fusion encoder into a state-conditioned one through multi-scale gated cross-attention. A near-identity gated residual preserves the base representation. Difference-aware Goal Cross-Attention then biases the attention scores using a per-token state-goal discrepancy map. On OGBench, DAGR improves navigation. Our ablations trace the gain to the gated residual, not to the difference bias that names the method. On manipulation and puzzle tasks it matches or falls below the base. DAGR is a structured refinement, not a universal improvement.
Steering large language models typically relies on linear, context-independent interventions in activation space, an assumption that recent work has challenged and that can induce an information bottleneck when a fixed representation must encode many behavioral distinctions. We introduce MetaSteer, a method that learns...
On-policy self-distillation uses a model as its own teacher to provide dense supervision for reasoning, often through reference-solution conditioning. Providing privileged information does not by itself ensure effective token-level supervision throughout long responses. We introduce Activation-Conditioned Self-Distilla...
Zhe-Xi Lu, Subhajit Chaudhury, Tejaswini Pedapati et al.· 1 citation
Large language models (LLMs) have demonstrated strong performance on structured reasoning tasks, but what they encode and whether it informs model behavior remain unclear. We investigate this question through geometric reasoning, using parametric CAD constraints as a controlled testbed for separating local pairwise rel...
M. Liang, Xin-Zhao Cheng, Faizan Wajid· 0 citations
Action-Conditioned Predictive Consistency (ACPC), a diagnostic that measures how far a clean history and a visually perturbed view of it diverge after being rolled forward under the same action sequence, is introduced and it is proved that this divergence bounds the perturbation-induced change in multi-step prediction...
Guo An, Zijing Wu, Hongzhuang Dong et al.· 3 citations
By coupling QAD's stable low-bit initialization with OPD's on-policy reasoning recovery, the framework provides a comprehensive sub-3-bit solution that preserves broad capabilities while restoring long-form reasoning.
Yuan-Teng Chen, Zhi-Lei Liu, Peisong Wang et al.· 0 citations
The results suggest that local action-comparison supervision can complement temporal prediction by encouraging JEPA-based representations to retain both long-horizon temporal structure and fine-grained distinctions among locally observed actions for offline zero-shot control.
Learn how Google DeepMind and GovTech Singapore uses lightweight on-device Gemma models to intercept conversational scams in private chats with zero cloud data egress.
